Paper Digest: IJCAI 2022 Highlights
International Joint Conference on Artificial Intelligence (IJCAI) is one of the top artificial intelligence conferences in the world. In 2022, it is to be held in Austria.
To help the community quickly catch up on the work presented in this conference, Paper Digest Team processed all accepted papers, and generated one highlight sentence (typically the main topic) for each paper. Readers are encouraged to read these machine generated highlights / summaries to quickly get the main idea of each paper.
Based in New York, Paper Digest is dedicated to helping people generate contents & reason over unstructured data. Different from black-box approaches, we build deep models on semantics, which allows results to be produced with explainations. Such models power this website, and are behind our services including “search engine”, “summarization”, “question answering”, and “literature review”.
If you do not want to miss interesting academic papers, you are welcome to sign up our daily paper digest service to get updates on new papers published in your area every day. You are also welcome to follow us on Twitter and Linkedin to get updated with new conference digests.
Paper Digest Team
New York City, New York, 10017
team@paperdigest.org
TABLE 1: Paper Digest: IJCAI 2022 Highlights
Paper | Author(s) | |
---|---|---|
1 | Anytime Capacity Expansion in Medical Residency Match By Monte Carlo Tree Search Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To tackle the problem, we propose an anytime method that the upper confidence tree searches the space of capacity expansions, each of which has a resident-optimal stable assignment that the deferred acceptance method finds. |
Kenshi Abe; Junpei Komiyama; Atsushi Iwasaki; |
2 | Socially Intelligent Genetic Agents for The Emergence of Explicit Norms Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We address the emergence of explicit norms by developing agents who provide and reason about explanations for norm violations in deciding sanctions and identifying alternative norms. |
Rishabh Agrawal; Nirav Ajmeri; Munindar Singh; |
3 | An EF2X Allocation Protocol for Restricted Additive Valuations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we investigate EFX for restricted additive valuations, that is, every good has a non-negative value, and every agent is interested in only some of the goods. |
Hannaneh Akrami; Rojin Rezvan; Masoud Seddighin; |
4 | Better Collective Decisions Via Uncertainty Reduction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We consider an agent community wishing to decide on several binary issues by means of issue-by-issue majority voting. |
Shiri Alouf-Heffetz; Laurent Bulteau; Edith Elkind; Nimrod Talmon; Nicholas Teh; |
5 | How Should We Vote? A Comparison of Voting Systems Within Social Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we investigate how different voting systems perform as a function of the characteristics of the underlying voting population and social network. |
Shiri Alouf-Heffetz; Ben Armstrong; Kate Larson; Nimrod Talmon; |
6 | Public Signaling in Bayesian Ad Auctions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we focus on public signaling and VCG mechanisms, under which bidders truthfully report their valuations. |
Francesco Bacchiocchi; Matteo Castiglioni; Alberto Marchesi; Giulia Romano; Nicola Gatti; |
7 | Mixed Strategies for Security Games with General Defending Requirements Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we initiate the study of mixed strategies for the security games in which the targets can have different defending requirements. |
Rufan Bai; Haoxing Lin; Xinyu Yang; Xiaowei Wu; Minming Li; Weijia Jia; |
8 | Envy-Free and Pareto-Optimal Allocations for Agents with Asymmetric Random Valuations Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we consider a generalization of this model where each agent’s utilities are drawn independently from a distribution specific to the agent. |
Yushi Bai; Paul Gölz; |
9 | Achieving Envy-Freeness with Limited Subsidies Under Dichotomous Valuations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study the problem of allocating indivisible goods among agents in a fair manner. |
Siddharth Barman; Anand Krishna; Yadati Narahari; Soumyarup Sadhukhan; |
10 | Transparency, Detection and Imitation in Strategic Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our model identifies key aspects related to strategic adaptation and the challenges that an institution could face as it attempts to provide explanations. |
Flavia Barsotti; Ruya Gokhan Kocer; Fernando P. Santos; |
11 | Time-Constrained Participatory Budgeting Under Uncertain Project Costs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, this will increase execution time drastically. We generalize existing frameworks to capture this setting, study desirable properties of algorithms for this problem, and show that some desirable properties are incompatible. |
Dorothea Baumeister; Linus Boes; Christian Laußmann; |
12 | Tolerance Is Necessary for Stability: Single-Peaked Swap Schelling Games Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, sociological polls suggest that real-world agents are actually favoring mixed-type neighborhoods, and hence should be modeled via non-monotone utility functions. To address this, we study Swap Schelling Games with single-peaked utility functions. |
Davide Bilò; Vittorio Bilò; Pascal Lenzner; Louise Molitor; |
13 | General Opinion Formation Games with Social Group Membership Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Modeling how agents form their opinions is of paramount importance for designing marketing and electoral campaigns. In this work, we present a new framework for opinion formation which generalizes the well-known Friedkin-Johnsen model by incorporating three important features: (i) social group membership, that limits the amount of influence that people not belonging to the same group may lead on a given agent; (ii) both attraction among friends, and repulsion among enemies; (iii) different strengths of influence lead from different people on a given agent, even if the social relationships among them are the same. |
Vittorio Bilò; Diodato Ferraioli; Cosimo Vinci; |
14 | Fair Equilibria in Sponsored Search Auctions: The Advertisers’ Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work we introduce a new class of mechanisms composed of a traditional Generalized Second Price (GSP) auction, and a fair division scheme in order to achieve some desired level of fairness between groups of Bayesian strategic advertisers. |
Georgios Birmpas; Andrea Celli; Riccardo Colini-Baldeschi; Stefano Leonardi; |
15 | Understanding Distance Measures Among Elections Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Motivated by putting empirical work based on (synthetic) election data on a more solid mathematical basis, we analyze six distances among elections, including, e.g., the challenging-to-compute but very precise swap distance and the distance used to form the so-called map of elections. |
Niclas Boehmer; Piotr Faliszewski; Rolf Niedermeier; Stanisław Szufa; Tomasz Wąs; |
16 | Toward Policy Explanations for Multi-Agent Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present novel methods to generate two types of policy explanations for MARL: (i) policy summarization about the agent cooperation and task sequence, and (ii) language explanations to answer queries about agent behavior. |
Kayla Boggess; Sarit Kraus; Lu Feng; |
17 | Distortion in Voting with Top-t Preferences Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we consider the setting where each agent ranks only her t favorite alternatives and identify almost tight bounds on the best possible distortion when selecting a single alternative or a committee of alternatives of a given size k. |
Allan Borodin; Daniel Halpern; Mohamad Latifian; Nisarg Shah; |
18 | Let’s Agree to Agree: Targeting Consensus for Incomplete Preferences Through Majority Dynamics Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study settings in which agents with incomplete preferences need to make a collective decision. |
Sirin Botan; Simon Rey; Zoi Terzopoulou; |
19 | Incentives in Social Decision Schemes with Pairwise Comparison Preferences Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Hence, we focus on the natural but little understood pairwise comparison (PC) preference extension, which postulates that one lottery is preferred to another if the former is more likely to return a preferred outcome. |
Felix Brandt; Patrick Lederer; Warut Suksompong; |
20 | Single-Peaked Opinion Updates Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We consider opinion diffusion for undirected networks with sequential updates when the opinions of the agents are single-peaked preference rankings. |
Robert Bredereck; Anne-Marie George; Jonas Israel; Leon Kellerhals; |
21 | When Votes Change and Committees Should (Not) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Being interested in a sequence of committees, we introduce two time-dependent multistage models based on simple scoring-based voting. |
Robert Bredereck; Till Fluschnik; Andrzej Kaczmarczyk; |
22 | Network Creation with Homophilic Agents Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study Network Creation Games with multiple types of homophilic agents and non-uniform edge cost, introducing two models focusing on the perception of same-type and different-type neighboring agents, respectively. |
Martin Bullinger; Pascal Lenzner; Anna Melnichenko; |
23 | VidyutVanika21: An Autonomous Intelligent Broker for Smart-grids Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The efficiency brought in by such brokers to the smart grid setup can be studied through a well-developed simulation environment. In this paper, we describe the design of one such energy broker called VidyutVanika21 (VV21) and analyze its performance using a simulation platform called PowerTAC (PowerTrading Agent Competition). |
Sanjay Chandlekar; Bala Suraj Pedasingu; Easwar Subramanian; Sanjay Bhat; Praveen Paruchuri; Sujit Gujar; |
24 | Optimal Anonymous Independent Reward Scheme Design Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: If the cost function is convex, we show the optimal AIRS can be formulated as a convex optimization problem and propose an efficient algorithm to solve it. |
Mengjing Chen; Pingzhong Tang; Zihe Wang; Shenke Xiao; Xiwang Yang; |
25 | Goal Consistency: An Effective Multi-Agent Cooperative Method for Multistage Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Inspired by human’s improving cooperation through goal consistency, we propose Multi-Agent Goal Consistency (MAGIC) framework to improve sample efficiency for learning in multi-stage tasks. |
Xinning Chen; Xuan Liu; Shigeng Zhang; Bo Ding; Kenli Li; |
26 | On The Convergence of Fictitious Play: A Decomposition Approach Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Although FP has provable convergence guarantees on zero-sum games and potential games, many real-world problems are often a mixture of both and the convergence property of FP has not been fully studied yet. In this paper, we extend the convergence results of FP to the combinations of such games and beyond. |
Yurong Chen; Xiaotie Deng; Chenchen Li; David Mguni; Jun Wang; Xiang Yan; Yaodong Yang; |
27 | Two-Sided Matching Over Social Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The main purpose of this paper is to clarify the existence of mechanisms that satisfy several properties that are classified into four criteria: incentive constraints, efficiency constraints, stability constraints, and fairness constraints. |
Sung-Ho Cho; Taiki Todo; Makoto Yokoo; |
28 | A Formal Model for Multiagent Q-Learning Dynamics on Regular Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The focus of previous research has been either on 2-agent settings or well-mixed infinitely large agent populations. In this paper, we consider the scenario where n Q-learning agents locate on regular graphs, such that agents can only interact with their neighbors. |
Chen Chu; Yong Li; Jinzhuo Liu; Shuyue Hu; Xuelong Li; Zhen Wang; |
29 | Preserving Consistency in Multi-Issue Liquid Democracy Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose instead to elicit and apply the agents’ priorities over the delegated issues, designing and analysing two algorithms that find consistent votes from the agents’ delegations in polynomial time. |
Rachael Colley; Umberto Grandi; |
30 | Voting in Two-Crossing Elections Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce two-crossing elections as a generalization of single-crossing elections, showing a number of new results. |
Andrei Constantinescu; Roger Wattenhofer; |
31 | Multi-Agent Intention Progression with Reward Machines Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: While this assumption is reasonable in some circumstances, it is less plausible when the agents are not co-designed. In this paper, we present a new approach to multi-agent intention scheduling in which agents predict the actions of other agents based on a high-level specification of the tasks performed by an agent in the form of a reward machine (RM) rather than on its (assumed) program. |
Michael Dann; Yuan Yao; Natasha Alechina; Brian Logan; John Thangarajah; |
32 | An Analysis of The Linear Bilateral ANAC Domains Using The MiCRO Benchmark Strategy Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The Automated Negotiating Agents Competition (ANAC) is an annual competition that compares the state-of-the-art algorithms in the field of automated negotiation. |
Dave De Jonge; |
33 | Approval with Runoff Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We define a family of runoff rules that work as follows: voters cast approval ballots over candidates; two finalists are selected; and the winner is decided by majority. |
Théo Delemazure; Jérôme Lang; Jean-François Laslier; M. Remzi Sanver; |
34 | The Complexity of Envy-Free Graph Cutting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We consider the problem of fairly dividing a set of heterogeneous divisible resources among agents with different preferences. |
Argyrios Deligkas; Eduard Eiben; Robert Ganian; Thekla Hamm; Sebastian Ordyniak; |
35 | Parameterized Complexity of Hotelling-Downs with Party Nominees Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We examine the complexity of deciding whether a pure Nash equilibrium exists for this model under several natural parameters: the number of different positions of the candidates, the discrepancy and the span of the nominees, and the overlap of the parties. We provide FPT and XP algorithms and we complement them with a W[1]-hardness result. |
Argyrios Deligkas; Eduard Eiben; Tiger-Lily Goldsmith; |
36 | Online Approval Committee Elections Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: (1) We assess to what extent the committees that are computed online can proportionally represent the voters. |
Virginie Do; Matthieu Hervouin; Jérôme Lang; Piotr Skowron; |
37 | On The Ordinal Invariance of Power Indices on Coalitional Games Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Among general games, we characterize those that are stable for a given linear index. |
Jean-Paul Doignon; Stefano Moretti; Meltem Ozturk; |
38 | Invasion Dynamics in The Biased Voter Process Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we study the problem of fixation probability maximization under this model: given a budget k, find a set of k agents to initiate the invasion that maximizes the fixation probability. |
Loke Durocher; Panagiotis Karras; Andreas Pavlogiannis; Josef Tkadlec; |
39 | Efficient Resource Allocation with Secretive Agents Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We consider the allocation of homogeneous divisible goods to agents with linear additive valuations. |
Soroush Ebadian; Rupert Freeman; Nisarg Shah; |
40 | Contests to Incentivize A Target Group Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We describe a symmetric Bayes–Nash equilibrium for contests that have two types of rank-based prizes: (1) prizes that are accessible only to the agents in the target group; (2) prizes that are accessible to everyone. |
Edith Elkind; Abheek Ghosh; Paul W. Goldberg; |
41 | Representation Matters: Characterisation and Impossibility Results for Interval Aggregation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In the context of aggregating intervals reflecting the views of several agents into a single interval, we investigate the impact of the form of representation chosen for the intervals involved. |
Ulle Endriss; Arianna Novaro; Zoi Terzopoulou; |
42 | Insight Into Voting Problem Complexity Using Randomized Classes Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We consider the problem of constructive control by replacing voters (CCRV) introduced by Loreggia et al. [2015, https://dl.acm.org/doi/10.5555/2772879.2773411] for the scoring rule First-Last, which is defined by (1, 0, …, 0, -1). |
Zack Fitzsimmons; Edith Hemaspaandra; |
43 | Approximate Strategyproof Mechanisms for The Additively Separable Group Activity Selection Problem Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We investigate strategyproof mechanisms in the Group Activity Selection Problem with the additively separable property. |
Michele Flammini; Giovanna Varricchio; |
44 | Picking The Right Winner: Why Tie-Breaking in Crowdsourcing Contests Matters Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a complete information game-theoretic model for crowdsourcing contests. |
Coral Haggiag; Sigal Oren; Ella Segev; |
45 | Can Buyers Reveal for A Better Deal? Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study market interactions in which buyers are allowed to credibly reveal partial information about their types to the seller. |
Daniel Halpern; Gregory Kehne; Jamie Tucker-Foltz; |
46 | Two for One & One for All: Two-Sided Manipulation in Matching Markets Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our main contribution is to develop polynomial-time algorithms for finding an optimal manipulation in both settings. |
Hadi Hosseini; Fatima Umar; Rohit Vaish; |
47 | Phragmén Rules for Degressive and Regressive Proportionality Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce a new family of rules that broadly generalize Phragmén’s Sequential Rule spanning the spectrum between degressive and regressive proportionality. |
Michał Jaworski; Piotr Skowron; |
48 | Forgiving Debt in Financial Network Games Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In particular, the financial authority may offer bailout money to some bank(s) or forgive the debts of others in order to maximize liquidity, and we examine efficient ways to achieve this. |
Panagiotis Kanellopoulos; Maria Kyropoulou; Hao Zhou; |
49 | On Discrete Truthful Heterogeneous Two-Facility Location Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We revisit the discrete heterogeneous two-facility location problem, in which there is a set of agents that occupy nodes of a line graph, and have private approval preferences over two facilities. |
Panagiotis Kanellopoulos; Alexandros A. Voudouris; Rongsen Zhang; |
50 | Plurality Veto: A Simple Voting Rule Achieving Optimal Metric Distortion Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: One after the other, voters decrement the score of their bottom choice among the standing candidates, and the last standing candidate wins. We give a one-paragraph proof that this voting rule achieves distortion 3. |
Fatih Erdem Kizilkaya; David Kempe; |
51 | The Dichotomous Affiliate Stable Matching Problem: Approval-Based Matching with Applicant-Employer Relations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This complete ordering restriction is unrealistic, and further the model may have an empty core. To address this, we introduce the Dichotomous Affiliate Stable Matching (DASM) Problem, where agents’ preferences indicate dichotomous acceptance or rejection of another agent in the marketplace, both for themselves and their affiliates. |
Marina Knittel; Samuel Dooley; John Dickerson; |
52 | Light Agents Searching for Hot Information Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We consider a system in which an agent receives an update, typically an insertion or deletion, of some information upon visiting a node. |
Dariusz R. Kowalski; Dominik Pajak; |
53 | Explaining Preferences By Multiple Patterns in Voters’ Behavior Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, sometimes a single axis or a decision tree is insufficient to capture the voters’ preferences; rather, there is a small number K of axes or decision trees such that each vote in the profile is consistent with one of these axes (resp., trees). In this work, we study the complexity of deciding whether voters’ preferences can be explained in this manner. |
Sonja Kraiczy; Edith Elkind; |
54 | Biased Majority Opinion Dynamics: Exploiting Graph K-domination Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we exhibit classes of network topologies for which we prove that the expected time for consensus on the superior opinion can be exponential. |
Hicham Lesfari; Frédéric Giroire; Stéphane Pérennes; |
55 | Modelling The Dynamics of Multi-Agent Q-learning: The Stochastic Effects of Local Interaction and Incomplete Information Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The theoretical underpinnings of multiagent reinforcement learning has recently attracted much attention. In this work, we focus on the generalized social learning (GSL) protocol — an agent interaction protocol that is widely adopted in the literature, and aim to develop an accurate theoretical model for the Q-learning dynamics under this protocol. |
Chin-wing Leung; Shuyue Hu; Ho-fung Leung; |
56 | Propositional Gossip Protocols Under Fair Schedulers Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Distributed epistemic gossip protocols use epistemic formulas in the component programs for the agents. In this paper, we study the simplest classes of such gossip protocols: propositional gossip protocols, in which whether an agent wants to initiate a call depends only on the set of secrets that the agent currently knows. |
Joseph Livesey; Dominik Wojtczak; |
57 | Proportional Budget Allocations: Towards A Systematization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We contribute to the programme of lifting proportionality axioms from the multi-winner voting setting to participatory budgeting. |
Maaike Los; Zoé Christoff; Davide Grossi; |
58 | Parameterized Algorithms for Kidney Exchange Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study parameterized algorithms for the kidney exchange problem in this paper. |
Arnab Maiti; Palash Dey; |
59 | Fixing Knockout Tournaments With Seeds Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We show that certain structural conditions that guarantee that a player can win a knockout tournament without seeds are no longer sufficient in light of seed constraints. |
Pasin Manurangsi; Warut Suksompong; |
60 | Group Wisdom at A Price: Jury Theorems with Costly Information Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In our setting voting involves the expenditure of some effort, which is required to achieve the appropriate level of competence, whereas abstention carries no effort. We model this scenario as a game and characterize its equilibria under several variations. |
Matteo Michelini; Adrian Haret; Davide Grossi; |
61 | Automated Synthesis of Mechanisms Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Mechanism Design aims to design a game so that a desirable outcome is reached regardless of agents’ self-interests. In this paper, we show how this problem can be rephrased as a synthesis problem, where mechanisms are automatically synthesized from a partial or complete specification in a high-level logical language. |
Munyque Mittelmann; Bastien Maubert; Aniello Murano; Laurent Perrussel; |
62 | Robust Solutions for Multi-Defender Stackelberg Security Games Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we introduce a robust model for MSSGs, which admits solutions that are resistant to small perturbations or uncertainties in the game’s parameters. |
Dolev Mutzari; Yonatan Aumann; Sarit Kraus; |
63 | I Will Have Order! Optimizing Orders for Fair Reviewer Assignment Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We model reviewer assignment as an instance of a fair allocation problem, presenting an extension of the classic round-robin mechanism, called Reviewer Round Robin (RRR). |
Justin Payan; Yair Zick; |
64 | Fair, Individually Rational and Cheap Adjustment Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Employing subsidies and tolls, we adjust the game so that choosing this predefined action profile becomes strictly dominant. Inspired mainly by the work of Monderer and Tennenholtz, where the promised subsidies do not materialise in the not played profiles, we provide a fair and individually rational game adjustment, such that the total outside investments sum up to zero at any profile, thereby facilitating easy and frequent usage of our adjustment without bearing costs, even if some players behave unexpectedly. |
Gleb Polevoy; Marcin Dziubiński; |
65 | Exploring The Benefits of Teams in Multiagent Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a new model of multiagent teams for reinforcement learning (RL) agents inspired by OP and early work on teams in artificial intelligence. |
David Radke; Kate Larson; Tim Brecht; |
66 | The Power of Media Agencies in Ad Auctions: Improving Utility Through Coordinated Bidding Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study the problem of finding bids and monetary transfers maximizing the utility of a group of colluders, under GSP and VCG mechanisms. |
Giulia Romano; Matteo Castiglioni; Alberto Marchesi; Nicola Gatti; |
67 | Transfer Learning Based Adaptive Automated Negotiating Agent Framework Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we present a simple yet effective method of learning an end-to-end negotiation strategy from historical negotiation data. |
Ayan Sengupta; Shinji Nakadai; Yasser Mohammad; |
68 | Multiwinner Elections Under Minimax Chamberlin-Courant Rule in Euclidean Space Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We consider multiwinner elections in Euclidean space using the minimax Chamberlin-Courant rule. |
Chinmay Sonar; Subhash Suri; Jie Xue; |
69 | Near-Tight Algorithms for The Chamberlin-Courant and Thiele Voting Rules Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present an almost optimal algorithm for the classic Chamberlin-Courant multiwinner voting rule (CC) on single-peaked preference profiles. |
Krzysztof Sornat; Virginia Vassilevska Williams; Yinzhan Xu; |
70 | Maxmin Participatory Budgeting Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose an algorithm that achieves for MPB, additive approximation guarantees for restricted spaces of instances and empirically show that our algorithm in fact gives exact optimal solutions on real-world PB datasets. |
Gogulapati Sreedurga; Mayank Ratan Bhardwaj; Yadati Narahari; |
71 | How to Sample Approval Elections? Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We extend the map-of-elections framework to the case of approval elections. |
Stanisław Szufa; Piotr Faliszewski; Łukasz Janeczko; Martin Lackner; Arkadii Slinko; Krzysztof Sornat; Nimrod Talmon; |
72 | Search-Based Testing of Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a search-based testing framework that enables a wide range of novel analysis capabilities for evaluating the safety and performance of deep RL agents. |
Martin Tappler; Filip Cano Córdoba; Bernhard K. Aichernig; Bettina Könighofer; |
73 | Real-Time BDI Agents: A Model and Its Implementation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we redefine the BDI agent control loop inspired by traditional and well establish algorithms for real-time systems to ensure a proper reaction of agents and their effective application in typical real-time domains. |
Andrea Traldi; Francesco Bruschetti; Marco Robol; Marco Roveri; Paolo Giorgini; |
74 | Max-Sum with Quadtrees for Decentralized Coordination in Continuous Domains Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we put forward a novel extension of the classic Max-Sum algorithm to the framework of Continuous Distributed Constrained Optimization Problems (Continuous DCOPs), by utilizing a popular geometric algorithm, namely Quadtrees. |
Dimitrios Troullinos; Georgios Chalkiadakis; Vasilis Samoladas; Markos Papageorgiou; |
75 | Strategy Proof Mechanisms for Facility Location with Capacity Limits Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We provide a comprehensive picture of strategy proof mechanisms for facility location problems with capacity constraints that are anonymous and Pareto optimal. |
Toby Walsh; |
76 | Modelling The Dynamics of Regret Minimization in Large Agent Populations: A Master Equation Approach Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we consider the scenario in which a population of infinitely many agents apply regret minimization in repeated symmetric games. |
Zhen Wang; Chunjiang Mu; Shuyue Hu; Chen Chu; Xuelong Li; |
77 | Monotone-Value Neural Networks: Exploiting Preference Monotonicity in Combinatorial Assignment Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, one major shortcoming of the ML algorithms that were used is their disregard of important prior knowledge about agents’ preferences. To address this, we introduce monotone-value neural networks (MVNNs), which are designed to capture combinatorial valuations, while enforcing monotonicity and normality. |
Jakob Weissteiner; Jakob Heiss; Julien Siems; Sven Seuken; |
78 | Fourier Analysis-based Iterative Combinatorial Auctions Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we bring the power of Fourier analysis to the design of combinatorial auctions (CAs). |
Jakob Weissteiner; Chris Wendler; Sven Seuken; Ben Lubin; Markus Püschel; |
79 | Manipulating Elections By Changing Voter Perceptions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a formal model of the impact of perception manipulation on election outcomes in the framework of spatial voting theory, in which the preferences of voters over candidates are generated based on their relative distance in the space of issues. |
Junlin Wu; Andrew Estornell; Lecheng Kong; Yevgeniy Vorobeychik; |
80 | Fast and Fine-grained Autoscaler for Streaming Jobs with Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel fine-grained autoscaler for streaming jobs based on reinforcement learning. |
Mingzhe Xing; Hangyu Mao; Zhen Xiao; |
81 | Mechanism Design with Predictions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper initiates the systematic study of mechanism design in this model. |
Chenyang Xu; Pinyan Lu; |
82 | Efficient Multi-Agent Communication Via Shapley Message Value Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, they do not explicitly evaluate each message’s value, failing to learn an efficient communication protocol in more complex scenarios. To tackle this issue, we model the teammates of an agent as a message coalition and calculate the Shapley Message Value (SMV) of each agent within it. |
Di Xue; Lei Yuan; Zongzhang Zhang; Yang Yu; |
83 | On The Complexity of Calculating Approval-Based Winners in Candidates-Embedded Metrics Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study approval-based multiwinner voting where candidates are in a metric space and committees are valuated in terms of their distances to the given votes. |
Yongjie Yang; |
84 | Environment Design for Biased Decision Makers Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we focus on the scenario in which the agent might exhibit biases in decision making. |
Guanghui Yu; Chien-Ju Ho; |
85 | Multi-Agent Concentrative Coordination with Decentralized Task Representation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, they fail to leverage the task structure decomposability, which generally exists in real-world multi-agent systems (MASs), leading to a significant amount of time exploring the optimal policy in complex scenarios. To address this limitation, we propose a novel framework Multi-Agent Concentrative Coordination (MACC) based on task decomposition, with which an agent can implicitly form local groups to reduce the learning space to facilitate coordination. |
Lei Yuan; Chenghe Wang; Jianhao Wang; Fuxiang Zhang; Feng Chen; Cong Guan; Zongzhang Zhang; Chongjie Zhang; Yang Yu; |
86 | Correlation-Based Algorithm for Team-Maxmin Equilibrium in Multiplayer Extensive-Form Games Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we focus on an alternative solution concept in zero-sum multiplayer extensive-form games called Team-Maxmin Equilibrium (TME). |
Youzhi Zhang; Bo An; V. S. Subrahmanian; |
87 | Strategyproof Mechanisms for Group-Fair Facility Location Problems Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our aim is to design mechanisms to locate a facility to approximately minimize the costs of groups of agents to the facility fairly while eliciting the agents’ locations truthfully. |
Houyu Zhou; Minming Li; Hau Chan; |
88 | Evolutionary Approach to Security Games with Signaling Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Incorporating both human and sensor defender resources strategically is the subject of recent work on Security Games with Signaling (SGS). |
Adam Żychowski; Jacek Mańdziuk; Elizabeth Bondi; Aravind Venugopal; Milind Tambe; Balaraman Ravindran; |
89 | Detecting Out-Of-Context Objects Using Graph Contextual Reasoning Network Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper presents an approach for detecting out-of-context (OOC) objects in images. |
Manoj Acharya; Anirban Roy; Kaushik Koneripalli; Susmit Jha; Christopher Kanan; Ajay Divakaran; |
90 | Axiomatic Foundations of Explainability Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This sheds light on the axioms which distinguish the two types of reasons. As a third contribution, the paper introduces various explainers of both families, and fully characterizes some of them. |
Leila Amgoud; Jonathan Ben-Naim; |
91 | On Preferred Abductive Explanations for Decision Trees and Random Forests Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Especially, better explanations than the one that is derived may exist. As a way to circumvent this issue, we propose to leverage a model of the explainee, making precise her / his preferences about explanations, and to compute only preferred explanations. |
Gilles Audemard; Steve Bellart; Louenas Bounia; Frederic Koriche; Jean-Marie Lagniez; Pierre Marquis; |
92 | Individual Fairness Guarantees for Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Working with a range of metrics, including the Mahalanobis distance, we propose a method to overapproximate the resulting optimisation problem using piecewise-linear functions to lower and upper bound the NN’s non-linearities globally over the input space. |
Elias Benussi; Andrea Patane’; Matthew Wicker; Luca Laurenti; Marta Kwiatkowska; |
93 | How Does Frequency Bias Affect The Robustness of Neural Image Classifiers Against Common Corruption and Adversarial Perturbations? Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Here, we take one step further to more directly study the frequency bias of a model through the lens of its Jacobians and its implication to model robustness. To achieve this, we propose Jacobian frequency regularization for models’ Jacobians to have a larger ratio of low-frequency components. |
Alvin Chan; Yew Soon Ong; Clement Tan; |
94 | Learn to Reverse DNNs from AI Programs Automatically Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To quantify the model leakage risk of on-device DNNs automatically, we propose NNReverse, the first learning-based method which can reverse DNNs from AI programs without domain knowledge. |
Simin Chen; Hamed Khanpour; Cong Liu; Wei Yang; |
95 | CAT: Customized Adversarial Training for Improved Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, we show it would lead worse training and generalizaiton error and forcing the prediction to match one-hot label. In this paper, therefore, we propose a new algorithm, named Customized Adversarial Training (CAT), which adaptively customizes the perturbation level and the corresponding label for each training sample in adversarial training. |
Minhao Cheng; Qi Lei; Pin-Yu Chen; Inderjit Dhillon; Cho-Jui Hsieh; |
96 | PPT: Backdoor Attacks on Pre-trained Models Via Poisoned Prompt Tuning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose to obtain the poisoned prompt for PLMs and corresponding downstream tasks by prompt tuning. |
Wei Du; Yichun Zhao; Boqun Li; Gongshen Liu; Shilin Wang; |
97 | SoFaiR: Single Shot Fair Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To achieve different points on the fairness-information plane, one must train different models. |
Xavier Gitiaux; Huzefa Rangwala; |
98 | Fairness Without The Sensitive Attribute Via Causal Variational Autoencoder Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To infer a sensitive information proxy, we introduce a new variational auto-encoding-based framework named SRCVAE that relies on knowledge of the underlying causal graph. |
Vincent Grari; Sylvain Lamprier; Marcin Detyniecki; |
99 | Taking Situation-Based Privacy Decisions: Privacy Assistants Working with Humans Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Ideally, software privacy assistants can help by making privacy decisions in different situations on behalf of the users. To realize this, we propose an agent-based model for a privacy assistant. |
Nadin Kökciyan; Pinar Yolum; |
100 | Model Stealing Defense Against Exploiting Information Leak Through The Interpretation of Deep Neural Nets Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose DeepDefense, the first defense mechanism that protects an AI model against model stealing attackers exploiting both class probabilities and interpretations. |
Jeonghyun Lee; Sungmin Han; Sangkyun Lee; |
101 | Investigating and Explaining The Frequency Bias in Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper discusses the frequency bias phenomenon in image classification tasks: the high-frequency components are actually much less exploited than the low- and mid- frequency components. |
Zhiyu Lin; Yifei Gao; Jitao Sang; |
102 | AttExplainer: Explain Transformer Via Attention By Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, the huge size of dimensions directly challenges these methods to quantitatively analyze the attention matrix. Therefore, in this paper, we propose a novel reinforcement learning (RL) based framework for Transformer explanation via attention matrix, namely AttExplainer. |
Runliang Niu; Zhepei Wei; Yan Wang; Qi Wang; |
103 | Counterfactual Interpolation Augmentation (CIA): A Unified Approach to Enhance Fairness and Explainability of DNN Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a novel bias-tailored data augmentation approach, Counterfactual Interpolation Augmentation (CIA), attempting to debias the training data by d-separating the spurious correlation between the target variable and the sensitive attribute. |
Yao Qiang; Chengyin Li; Marco Brocanelli; Dongxiao Zhu; |
104 | BayCon: Model-agnostic Bayesian Counterfactual Generator Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To complicate matters even more, ensuring that the contrastive instances are optimised for feature sparsity, remain close to the explained instance, and are not drawn from outside of the data manifold, is far from trivial. To address this gap we propose BayCon: a novel counterfactual generator based on probabilistic feature sampling and Bayesian optimisation. |
Piotr Romashov; Martin Gjoreski; Kacper Sokol; Maria Vanina Martinez; Marc Langheinrich; |
105 | What Does My GNN Really Capture? On Exploring Internal GNN Representations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this article, we propose a method that goes further and isolates the internal features, hidden in the network layers, that are automatically identified by the GNN and used in the decision process. |
Luca Veyrin-Forrer; Ataollah Kamal; Stefan Duffner; Marc Plantevit; Céline Robardet; |
106 | Shielding Federated Learning: Robust Aggregation with Adaptive Client Selection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Although the problem has gained significant attention, existing defenses have several flaws: the server irrationally chooses malicious clients for aggregation even after they have been detected in previous rounds; the defenses perform ineffectively against sybil attacks or in the heterogeneous data setting. To overcome these issues, we propose MAB-RFL, a new method for robust aggregation in FL. |
Wei Wan; Shengshan Hu; jianrong Lu; Leo Yu Zhang; Hai Jin; Yuanyuan He; |
107 | Anti-Forgery: Towards A Stealthy and Robust DeepFake Disruption Attack Via Adversarial Perceptual-aware Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we investigate the vulnerability of the existing forgery techniques and propose a novel anti-forgery technique that helps users protect the shared facial images from attackers who are capable of applying the popular forgery techniques. |
Run Wang; Ziheng Huang; Zhikai Chen; Li Liu; Jing Chen; Lina Wang; |
108 | Cluster Attack: Query-based Adversarial Attacks on Graph with Graph-Dependent Priors Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose Cluster Attack — a Graph Injection Attack (GIA) on node classification, which injects fake nodes into the original graph to degenerate the performance of graph neural networks (GNNs) on certain victim nodes while affecting the other nodes as little as possible. |
Zhengyi Wang; Zhongkai Hao; Ziqiao Wang; Hang Su; Jun Zhu; |
109 | MetaFinger: Fingerprinting The Deep Neural Networks with Meta-training Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, existing fingerprint methods fingerprint the decision boundary by adversarial examples, which is not robust to model modification and adversarial defenses. To fill this gap, we propose a robust fingerprint method MetaFinger, which fingerprints the inner decision area of the model by meta-training, rather than the decision boundary. |
Kang Yang; Run Wang; Lina Wang; |
110 | Approximately EFX Allocations for Indivisible Chores Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we study how to fairly allocate a set of m indivisible chores to a group of n agents, each of which has a general additive cost function on the items. |
Shengwei Zhou; Xiaowei Wu; |
111 | MotionMixer: MLP-based 3D Human Body Pose Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we present MotionMixer, an efficient 3D human body pose forecasting model based solely on multi-layer perceptrons (MLPs). |
Arij Bouazizi; Adrian Holzbock; Ulrich Kressel; Klaus Dietmayer; Vasileios Belagiannis; |
112 | Event-driven Video Deblurring Via Spatio-Temporal Relation-Aware Network Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, this strategy neither considers the pixel-level spatial brightness changes nor the temporal correlation between events at each time step, resulting in insufficient use of spatio-temporal information. To address this issue, we propose a new Spatio-Temporal Relation-Attention network (STRA), for the specific event-based video deblurring. |
Chengzhi Cao; Xueyang Fu; Yurui Zhu; Gege Shi; Zheng-Jun Zha; |
113 | KPN-MFI: A Kernel Prediction Network with Multi-frame Interaction for Video Inverse Tone Mapping Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Considering both the intra-frame quality and the inter-frame consistency of a video, this article presents a new video iTM method based on a kernel prediction network (KPN), which takes advantage of multi-frame interaction (MFI) module to capture temporal-spatial information for video data. |
Gaofeng Cao; Fei Zhou; Han Yan; Anjie Wang; Leidong Fan; |
114 | Zero-Shot Logit Adjustment Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: The development of generative models enables current GZSL techniques to probe further into the semantic-visual link, culminating in a two-stage form that includes a generator and a classifier. |
Dubing Chen; Yuming Shen; Haofeng Zhang; Philip H.S. Torr; |
115 | Uncertainty-Aware Representation Learning for Action Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose an uncertainty-aware representation Learning (UARL) method for action segmentation. |
Lei Chen; Muheng Li; Yueqi Duan; Jie Zhou; Jiwen Lu; |
116 | AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose AutoAlign, an automatic feature fusion strategy for 3D object detection. |
Zehui Chen; Zhenyu Li; Shiquan Zhang; Liangji Fang; Qinhong Jiang; Feng Zhao; Bolei Zhou; Hang Zhao; |
117 | Unsupervised Multi-Modal Medical Image Registration Via Discriminator-Free Image-to-Image Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a novel translation-based unsupervised deformable image registration approach to convert the multi-modal registration problem to a mono-modal one. |
Zekang Chen; Jia Wei; Rui Li; |
118 | SpanConv: A New Convolution Via Spanning Kernel Space for Lightweight Pansharpening Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we focus on kernel generation and present an interpretable span strategy, named SpanConv, for the effective construction of kernel space. |
Zhi-Xuan Chen; Cheng Jin; Tian-Jing Zhang; Xiao Wu; Liang-Jian Deng; |
119 | Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we make an early effort to consider dehazing robustness under variational haze density, which is a realistic while under-studied problem in the research filed of singe image dehazing. To properly address this problem, we propose a novel density-variational learning framework to improve the robustness of the image dehzing model assisted by a variety of negative hazy images, to better deal with various complex hazy scenarios. |
De Cheng; Yan Li; Dingwen Zhang; Nannan Wang; Xinbo Gao; Jiande Sun; |
120 | I²R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present the Intra- and Inter-Human Relation Networks I²R-Net for Multi-Person Pose Estimation. |
Yiwei Ding; Wenjin Deng; Yinglin Zheng; Pengfei Liu; Meihong Wang; Xuan Cheng; Jianmin Bao; Dong Chen; Ming Zeng; |
121 | Region-Aware Metric Learning for Open World Semantic Segmentation Via Meta-Channel Aggregation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: The current state-of-the-art (SOTA) method, Deep Metric Learning Network (DMLNet), relies on pixel-level metric learning, with which the identification of similar regions having different semantics is difficult. Therefore, we propose a method called region-aware metric learning (RAML), which first separates the regions of the images and generates region-aware features for further metric learning. |
Hexin Dong; Zifan Chen; Mingze Yuan; Yutong Xie; Jie Zhao; Fei Yu; Bin Dong; Li Zhang; |
122 | MNet: Rethinking 2D/3D Networks for Anisotropic Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, a novel mesh network (MNet) is proposed to balance the spatial representation inter axes via learning. |
Zhangfu Dong; Yuting He; Xiaoming Qi; Yang Chen; Huazhong Shu; Jean-Louis Coatrieux; Guanyu Yang; Shuo Li; |
123 | ICGNet: Integration Context-based Reverse-Contour Guidance Network for Polyp Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, it is still a challenging task due to: (1)the boundary between the polyp and the background is blurred makes delineation difficult; (2)the various size and shapes causes feature representation of polyps difficult. In this paper, we propose an integration context-based reverse-contour guidance network (ICGNet) to solve these challenges. |
Xiuquan Du; Xuebin Xu; Kunpeng Ma; |
124 | SVTR: Scene Text Recognition with A Single Visual Model Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this study, we propose a Single Visual model for Scene Text recognition within the patch-wise image tokenization framework, which dispenses with the sequential modeling entirely. |
Yongkun Du; Zhineng Chen; Caiyan Jia; Xiaoting Yin; Tianlun Zheng; Chenxia Li; Yuning Du; Yu-Gang Jiang; |
125 | Learning Coated Adversarial Camouflages for Object Detectors Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, the 2D patch attached to a 3D object tends to suffer from an inevitable reduction in attack performance as the viewpoint changes. To remedy this issue, this work proposes the Coated Adversarial Camouflage (CAC) to attack the detectors in arbitrary viewpoints. |
Yexin Duan; Jialin Chen; Xingyu Zhou; Junhua Zou; Zhengyun He; Jin Zhang; Wu Zhang; Zhisong Pan; |
126 | D-DPCC: Deep Dynamic Point Cloud Compression Via 3D Motion Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a novel 3D sparse convolution-based Deep Dynamic Point Cloud Compression (D-DPCC) network to compensate and compress the DPC geometry with 3D motion estimation and motion compensation in the feature space. |
Tingyu Fan; Linyao Gao; Yiling Xu; Zhu Li; Dong Wang; |
127 | SparseTT: Visual Tracking with Sparse Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, self-attention lacks focusing on the most relevant information in the search regions, making it easy to be distracted by background. In this paper, we relieve this issue with a sparse attention mechanism by focusing the most relevant information in the search regions, which enables a much accurate tracking. |
Zhihong Fu; Zehua Fu; Qingjie Liu; Wenrui Cai; Yunhong Wang; |
128 | Lightweight Bimodal Network for Single-Image Super-Resolution Via Symmetric CNN and Recursive Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, these methods are difficult to be applied in real-world scenarios since they are inevitably accompanied by the problems of computational and memory costs caused by the complex operations. To solve this issue, we propose a Lightweight Bimodal Network (LBNet) for SISR. |
Guangwei Gao; Zhengxue Wang; Juncheng Li; Wenjie Li; Yi Yu; Tieyong Zeng; |
129 | Region-Aware Temporal Inconsistency Learning for DeepFake Video Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To effectively and comprehensively capture the various inconsistency, in this paper, we propose a novel Region-Aware Temporal Filter (RATF) module which automatically generates corresponding temporal filters for different spatial regions. |
Zhihao Gu; Taiping Yao; Yang Chen; Ran Yi; Shouhong Ding; Lizhuang Ma; |
130 | Learning Target-aware Representation for Visual Tracking Via Informative Interactions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we approach the problem by conducting multiple branch-wise interactions inside the Siamese-like backbone networks (InBN). |
Mingzhe Guo; Zhipeng Zhang; Heng Fan; Liping Jing; Yilin Lyu; Bing Li; Weiming Hu; |
131 | Exploring Fourier Prior for Single Image Rain Removal Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we develop a two-stage model where the first stage restores the amplitude of rainy images to clean rain streaks, and the second stage restores the phase information to refine fine-grained background structures. |
Xin Guo; Xueyang Fu; Man Zhou; Zhen Huang; Jialun Peng; Zheng-Jun Zha; |
132 | Rethinking Image Aesthetics Assessment: Models, Datasets and Benchmarks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: 2) We develop a baseline model, TANet, which can effectively extract theme information and adaptively establish perception rules to evaluate images with different themes. |
Shuai He; Yongchang Zhang; Rui Xie; Dongxiang Jiang; Anlong Ming; |
133 | Self-supervised Semantic Segmentation Grounded in Visual Concepts Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a self-supervised pixel representation learning method for semantic segmentation by using visual concepts (i.e., groups of pixels with semantic meanings, such as parts, objects, and scenes) extracted from images. |
Wenbin He; William Surmeier; Arvind Kumar Shekar; Liang Gou; Liu Ren; |
134 | Semantic Compression Embedding for Generative Zero-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Consequently, seen classes are indistinguishable, and the knowledge transfer from seen to unseen classes is limited. To tackle this issue, we propose a novel Semantic Compression Embedding Guided Generation (SC-EGG) model, which cascades a semantic compression embedding network (SCEN) and an embedding guided generative network (EGGN). |
Ziming Hong; Shiming Chen; Guo-Sen Xie; Wenhan Yang; Jian Zhao; Yuanjie Shao; Qinmu Peng; Xinge You; |
135 | ScaleFormer: Revisiting The Transformer-based Backbones from A Scale-wise
Perspective for Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, there are mainly two challenges in a scale-wise perspective: (1) intra-scale problem: the existing methods lacked in extracting local-global cues in each scale, which may impact the signal propagation of small objects; (2) inter-scale problem: the existing methods failed to explore distinctive information from multiple scales, which may hinder the representation learning from objects with widely variable size, shape and location. To address these limitations, we propose a novel backbone, namely ScaleFormer, with two appealing designs: (1) A scale-wise intra-scale transformer is designed to couple the CNN-based local features with the transformer-based global cues in each scale, where the row-wise and column-wise global dependencies can be extracted by a lightweight Dual-Axis MSA. |
Huimin Huang; Shiao Xie; Lanfen Lin; Yutaro Iwamoto; Xian-Hua Han; Yen-Wei Chen; Ruofeng Tong; |
136 | AQT: Adversarial Query Transformers for Domain Adaptive Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present AQT (adversarial query transformers) to integrate adversarial feature alignment into detection transformers. |
Wei-Jie Huang; Yu-Lin Lu; Shih-Yao Lin; Yusheng Xie; Yen-Yu Lin; |
137 | DANet: Image Deraining Via Dynamic Association Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, the correlation of these two components is barely considered, leading to unsatisfied deraining results. To this end, we propose a dynamic associated network (DANet) to achieve the association learning between rain streak removal and background recovery. |
Kui Jiang; Zhongyuan Wang; Zheng Wang; Peng Yi; Junjun Jiang; Jinsheng Xiao; Chia-Wen Lin; |
138 | SatFormer: Saliency-Guided Abnormality-Aware Transformer for Retinal Disease Classification in Fundus Image Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Therefore, without a comprehensive understanding of features from different lesion regions, they are vulnerable to noise from complex backgrounds and suffer from misclassification failures. In this paper, we address these limitations with a novel saliency-guided abnormality-aware transformer which explicitly captures the correlation between different lesion features from a global perspective with enhanced pathological semantics. |
Yankai Jiang; Ke Xu; Xinyue Wang; Yuan Li; Hongguang Cui; Yubo Tao; Hai Lin; |
139 | Domain Generalization Through The Lens of Angular Invariance Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we simply take DNNs as feature extractors to relax the requirement of distribution alignment. |
Yujie Jin; Xu Chu; Yasha Wang; Wenwu Zhu; |
140 | Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper presents a novel hybrid representation learning framework for streaming data, where an image frame in a video is modeled by an ensemble of two distinct deep neural networks; one is a low-bit quantized network and the other is a lightweight full-precision network. |
Ilchae Jung; Minji Kim; Eunhyeok Park; Bohyung Han; |
141 | Robustifying Vision Transformer Without Retraining from Scratch By Test-Time Class-Conditional Feature Alignment Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Based on the observation, we propose a new test-time adaptation method called class-conditional feature alignment (CFA), which minimizes both the class-conditional distribution differences and the whole distribution differences of the hidden representation between the source and target in an online manner. |
Takeshi Kojima; Yutaka Matsuo; Yusuke Iwasawa; |
142 | Attention-guided Contrastive Hashing for Long-tailed Image Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Toward that end, this paper introduces a simple yet effective model named Attention-guided Contrastive Hashing Network (ACHNet) for long-tailed hashing. |
Xuan Kou; Chenghao Xu; Xu Yang; Cheng Deng; |
143 | Beyond The Prototype: Divide-and-conquer Proxies for Few-shot Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Existing approaches typically follow the prototype learning paradigm to perform meta-inference, which fails to fully exploit the underlying information from support image-mask pairs, resulting in various segmentation failures, e.g., incomplete objects, ambiguous boundaries, and distractor activation. To this end, we propose a simple yet versatile framework in the spirit of divide-and-conquer. |
Chunbo Lang; Binfei Tu; Gong Cheng; Junwei Han; |
144 | PlaceNet: Neural Spatial Representation Learning with Multimodal Attention Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, previous approaches have been mainly evaluated on simple environments, or focused only on high-resolution rendering of small-scale scenes, hampering generalization of the representations to various spatial variability. To address this, we present PlaceNet, a neural representation that learns through random observations in a self-supervised manner, and represents observed scenes with triplet attention using visual, topographic, and semantic cues. |
Chung-Yeon Lee; Youngjae Yoo; Byoung-Tak Zhang; |
145 | What Is Right for Me Is Not Yet Right for You: A Dataset for Grounding Relative Directions Via Multi-Task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We investigate the challenging problem of grounding relative directions with end-to-end neural networks. |
Jae Hee Lee; Matthias Kerzel; Kyra Ahrens; Cornelius Weber; Stefan Wermter; |
146 | Learning to Assemble Geometric Shapes Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We demonstrate the effectiveness on shape assembly tasks with various scenarios, including the ones with abnormal fragments (e.g., missing and distorted), the different number of fragments, and different rotation discretization. |
Jinhwi Lee; Jungtaek Kim; Hyunsoo Chung; Jaesik Park; Minsu Cho; |
147 | Iterative Geometry-Aware Cross Guidance Network for Stereo Image Inpainting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To achieve it, we propose an Iterative Geometry-Aware Cross Guidance Network (IGGNet). |
Ang Li; Shanshan Zhao; Zhang Qingjie; Qiuhong Ke; |
148 | Representation Learning for Compressed Video Action Recognition Via Attentive Cross-modal Interaction with Motion Enhancement Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address the two issues above, this paper proposes a novel framework, namely Attentive Cross-modal Interaction Network with Motion Enhancement (MEACI-Net). |
Bing Li; Jiaxin Chen; Dongming Zhang; Xiuguo Bao; Di Huang; |
149 | Self-Guided Hard Negative Generation for Unsupervised Person Re-Identification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In result, the hard negative samples, playing important role in training reID models, are significantly reduced. To alleviate this problem, we propose a self-guided hard negative generation method for unsupervised person re-ID. |
Dongdong Li; Zhigang Wang; Jian Wang; Xinyu Zhang; Errui Ding; Jingdong Wang; Zhaoxiang Zhang; |
150 | MMNet: Muscle Motion-Guided Network for Micro-Expression Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To model the subtle facial muscle motions, we propose a robust micro-expression recognition (MER) framework, namely muscle motion-guided network (MMNet). |
Hanting Li; Mingzhe Sui; Zhaoqing Zhu; Feng Zhao; |
151 | ER-SAN: Enhanced-Adaptive Relation Self-Attention Network for Image Captioning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose to enhance the correlations between objects from a comprehensive view that jointly considers explicit semantic and geometric relations, generating plausible captions with accurate relationship predictions. |
Jingyu Li; Zhendong Mao; Shancheng Fang; Hao Li; |
152 | RePFormer: Refinement Pyramid Transformer for Robust Facial Landmark Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we formulate the facial landmark detection task as refining landmark queries along pyramid memories. |
Jinpeng Li; Haibo Jin; Shengcai Liao; Ling Shao; Pheng-Ann Heng; |
153 | Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To address these problems, we present a Dynamic lightweight High-Resolution Network (Dite-HRNet), which can efficiently extract multi-scale contextual information and model long-range spatial dependency for human pose estimation. Specifically, we propose two methods, dynamic split convolution and adaptive context modeling, and embed them into two novel lightweight blocks, which are named dynamic multi-scale context block and dynamic global context block. |
Qun Li; Ziyi Zhang; Fu Xiao; Feng Zhang; Bir Bhanu; |
154 | Learning Graph-based Residual Aggregation Network for Group Activity Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, a novel Graph-based Residual AggregatIon Network (GRAIN) is proposed to model the differences among all persons of the whole group, which is end-to-end trainable. |
Wei Li; Tianzhao Yang; Xiao Wu; Zhaoquan Yuan; |
155 | TCCNet: Temporally Consistent Context-Free Network for Semi-supervised Video Polyp Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, existing methods are limited in three respects: 1) most of them work on static images, while ignoring the temporal information in consecutive video frames; 2) all of them are fully supervised and easily overfit in presence of limited annotations; 3) the context of polyp (i.e., lumen, specularity and mucosa tissue) varies in an endoscopic clip, which may affect the predictions of adjacent frames. To resolve these challenges, we propose a novel Temporally Consistent Context-Free Network (TCCNet) for semi-supervised VPS. |
Xiaotong Li; Jilan Xu; Yuejie Zhang; Rui Feng; Rui-Wei Zhao; Tao Zhang; Xuequan Lu; Shang Gao; |
156 | PRNet: Point-Range Fusion Network for Real-Time LiDAR Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we introduce an end-to-end point-range fusion network (PRNet) that extracts semantic features mainly on the RV and iteratively fuses the RV features back to the 3D points for the final prediction. |
Xiaoyan Li; Gang Zhang; Tao Jiang; Xufen Cai; Zhenhua Wang; |
157 | Unsupervised Embedding and Association Network for Multi-Object Tracking Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, most previous methods equipped with embedding features heavily rely on manual identity annotations, which bring a high cost for the multi-object tracking (MOT) task. To address the above problem, we present an unsupervised embedding and association network (UEANet) for learning discriminative embedding features with pseudo identity labels. |
Yu-Lei Li; |
158 | Multi-View Visual Semantic Embedding Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a Multi-View Visual Semantic Embedding (MV-VSE) framework, which learns multiple embeddings for one visual data and explicitly models intra-class variations. |
Zheng Li; Caili Guo; Zerun Feng; Jenq-Neng Hwang; Xijun Xue; |
159 | Self-supervised Learning and Adaptation for Single Image Dehazing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we show that exploiting large scale training set and adapting to real hazy images are two critical issues in learning effective deep dehazing models. |
Yudong Liang; Bin Wang; Wangmeng Zuo; Jiaying Liu; Wenqi Ren; |
160 | Feature Dense Relevance Network for Single Image Dehazing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a novel dehazing network by defining the Feature Dense Relevance module (FDR) and the Shallow Feature Mapping module (SFM). |
Yun Liang; Enze Huang; Zifeng Zhang; Zhuo Su; Dong Wang; |
161 | RMGN: A Regional Mask Guided Network for Parser-free Virtual Try-on Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To address the aforementioned issue, we propose a novel PF method named Regional Mask Guided Network (RMGN). |
Chao Lin; Zhao Li; Sheng Zhou; Shichang Hu; Jialun Zhang; Linhao Luo; Jiarun Zhang; Longtao Huang; Yuan He; |
162 | Learning to Estimate Object Poses Without Real Image Annotations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We find that, in most cases, the synthetically trained pose estimators are able to provide reasonable initialization for depth-based pose refinement methods which yield accurate pose estimates. Motivated by this, we propose a novel learning framework, which utilizes the accurate results of depth-based pose refinement methods to supervise the RGB-based pose estimator. |
Haotong Lin; Sida Peng; Zhize Zhou; Xiaowei Zhou; |
163 | Intrinsic Image Decomposition By Pursuing Reflectance Image Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we investigate the possibilities of only using reflectance images for supervision during training. |
Tzu-Heng Lin; Pengxiao Wang; Yizhou Wang; |
164 | FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, most existing quantization methods have been developed mainly on Convolutional Neural Networks (CNNs), and suffer severe degradation when applied to fully quantized vision transformers. In this work, we demonstrate that many of these difficulties arise because of serious inter-channel variation in LayerNorm inputs, and present, Power-of-Two Factor (PTF), a systematic method to reduce the performance degradation and inference complexity of fully quantized vision transformers. |
Yang Lin; Tianyu Zhang; Peiqin Sun; Zheng Li; Shuchang Zhou; |
165 | MA-ViT: Modality-Agnostic Vision Transformers for Face Anti-Spoofing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we present a single branch based Transformer framework, namely Modality-Agnostic Vision Transformer (MA-ViT), which aims to improve the performance of arbitrary modal attacks with the help of multi-modal data. |
Ajian Liu; Yanyan Liang; |
166 | Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, these hand-crafted window partition mechanisms are data-agnostic and ignore their input content, so it is likely that one query maybe attend to irrelevant keys/values. To address this issue, we propose a Dynamic Group Attention (DG-Attention), which dynamically divides all queries into multiple groups and selects the most relevant keys/values for each group. |
Kai Liu; Tianyi Wu; Cong Liu; Guodong Guo; |
167 | Cost Ensemble with Gradient Selecting for GANs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In contrast, multiple discriminators with different cost functions can yield various gradients for the generator, which indicates we can use them to search for more transportation maps in the latent space. Inspired by this, we have proposed a framework to combat the mode collapse problem, containing multiple discriminators with different cost functions, named CES-GAN. |
Minghui Liu; Jiali Deng; Meiyi Yang; Xuan Cheng; Nianbo Liu; Ming Liu; Xiaomin Wang; |
168 | TopoSeg: Topology-aware Segmentation for Point Clouds Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, focusing on the perspective of topology awareness. |
Weiquan Liu; Hanyun Guo; Weini Zhang; Yu Zang; Cheng Wang; Jonathan Li; |
169 | Biological Instance Segmentation with A Superpixel-Guided Graph Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, existing methods are vulnerable to local imaging artifacts and similar object appearances, resulting in over-merge and over-segmentation. To reduce these two kinds of errors, we propose a new biological instance segmentation framework based on a superpixel-guided graph, which consists of two stages, i.e., superpixel-guided graph construction and superpixel agglomeration. |
Xiaoyu Liu; Wei Huang; Yueyi Zhang; Zhiwei Xiong; |
170 | Vision Shared and Representation Isolated Network for Person Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The inevitable conflict greatly restricts the researches on the one-stage person search methods. To address this issue, we propose a Vision Shared and Representation Isolated (VSRI) network to decouple the two conflicted subtasks simultaneously, through which two independent representations are constructed for the two subtasks. |
Yang Liu; Yingping Li; Chengyu Kong; Yuqiu Kong; Shenglan Liu; Feilong Wang; |
171 | Copy Motion From One to Another: Fake Motion Video Generation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Furthermore, current methods typically employ GANs with a L2 loss to assess the authenticity of the generated videos, inherently requiring a large amount of training samples to learn the texture details for adequate video generation. In this work, we tackle these challenges from three aspects: 1) We disentangle each video frame into foreground (the person) and background, focusing on generating the foreground to reduce the underlying dimension of the network output. |
Zhenguang Liu; Sifan Wu; Chejian Xu; Xiang Wang; Lei Zhu; Shuang Wu; Fuli Feng; |
172 | Deep Video Harmonization With Color Mapping Consistency Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we construct a new video harmonization dataset HYouTube by adjusting the foreground of real videos to create synthetic composite videos. |
Xinyuan Lu; Shengyuan Huang; Li Niu; Wenyan Cong; Liqing Zhang; |
173 | Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper proposes an AU relationship modelling approach that deep learns a unique graph to explicitly describe the relationship between each pair of AUs of the target facial display. |
Cheng Luo; Siyang Song; Weicheng Xie; Linlin Shen; Hatice Gunes; |
174 | Long-Short Term Cross-Transformer in Compressed Domain for Few-Shot Video Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: On the other hand, the heuristic model simply encodes the equally treated frames in sequence, which results in the lack of both long-term and short-term temporal modeling and interaction. To alleviate these limitations, we take advantage of the compressed domain knowledge and propose a long-short term Cross-Transformer (LSTC) for few-shot video classification. |
Wenyang Luo; Yufan Liu; Bing Li; Weiming Hu; Yanan Miao; Yangxi Li; |
175 | Improved Deep Unsupervised Hashing with Fine-grained Semantic Similarity Mining for Multi-Label Image Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we study deep unsupervised hashing, a critical problem for approximate nearest neighbor research. |
Zeyu Ma; Xiao Luo; Yingjie Chen; Mixiao Hou; Jinxing Li; Minghua Deng; Guangming Lu; |
176 | Learning Degradation Uncertainty for Unsupervised Real-world Image Super-resolution Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, most of the existing work ignores the degradation uncertainty of the generated realistic LR images, since only one LR image has been generated given an HR image. To address this weakness, we propose learning the degradation uncertainty of generated LR images and sampling multiple LR images from the learned LR image (mean) and degradation uncertainty (variance) and construct LR-HR pairs to train the super-resolution (SR) networks. |
Qian Ning; Jingzhu Tang; Fangfang Wu; Weisheng Dong; Xin Li; Guangming Shi; |
177 | Continual Semantic Segmentation Leveraging Image-level Labels and Rehearsal Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Indeed, in incremental learning scenarios, where new classes are added to an existing framework, these models are prone to catastrophic forgetting of previous classes. To address these two limitations, we propose a weakly-supervised mechanism for continual semantic segmentation that can leverage cheap image-level annotations and a novel rehearsal strategy that intertwines the learning of past and new classes. |
Mathieu Pagé Fortin; Brahim Chaib-draa; |
178 | Multilevel Hierarchical Network with Multiscale Sampling for Video Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: While most existing approaches ignore the visual appearance-motion information at different temporal scales, it is unknown how to incorporate the multilevel processing capacity of a deep learning model with such multiscale information. Targeting these issues, this paper proposes a novel Multilevel Hierarchical Network (MHN) with multiscale sampling for VideoQA. |
Min Peng; Chongyang Wang; Yuan Gao; Yu Shi; Xiang-Dong Zhou; |
179 | Source-Adaptive Discriminative Kernels Based Network for Remote Sensing Pansharpening Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a convolution network with source-adaptive discriminative kernels, called ADKNet, for the pansharpening task. |
Siran Peng; Liang-Jian Deng; Jin-Fan Hu; Yuwei Zhuo; |
180 | SimMC: Simple Masked Contrastive Learning of Skeleton Representations for Unsupervised Person Re-Identification Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we focus on unsupervised skeleton-based person re-ID, and present a generic Simple Masked Contrastive learning (SimMC) framework to learn effective representations from unlabeled 3D skeletons for person re-ID. |
Haocong Rao; Chunyan Miao; |
181 | ChimeraMix: Image Classification on Small Datasets Via Masked Feature Mixing Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we address the problem of learning deep neural networks on small datasets. |
Christoph Reinders; Frederik Schubert; Bodo Rosenhahn; |
182 | IDPT: Interconnected Dual Pyramid Transformer for Face Super-Resolution Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel and effective face super-resolution framework based on Transformer, namely Interconnected Dual Pyramid Transformer (IDPT). |
Jingang Shi; Yusi Wang; Songlin Dong; Xiaopeng Hong; Zitong Yu; Fei Wang; Changxin Wang; Yihong Gong; |
183 | A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a unified framework to generate feasible adversarial examples that satisfy given domain constraints. |
Thibault Simonetto; Salijona Dyrmishi; Salah Ghamizi; Maxime Cordy; Yves Le Traon; |
184 | Emotion-Controllable Generalized Talking Face Generation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a one-shot facial geometry-aware emotional talking face generation method that can generalize to arbitrary faces. |
Sanjana Sinha; Sandika Biswas; Ravindra Yadav; Brojeshwar Bhowmick; |
185 | Harnessing Fourier Isovists and Geodesic Interaction for Long-Term Crowd Flow Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, the input representations, models, and datasets for LTCFP are currently limited. To this end, we propose Fourier Isovists, a novel input representation based on egocentric visibility, which consistently improves all existing models. |
Samuel S. Sohn; Seonghyeon Moon; Honglu Zhou; Mihee Lee; Sejong Yoon; Vladimir Pavlovic; Mubbasir Kapadia; |
186 | Boundary-Guided Camouflaged Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Existing deep-learning methods often fall into the difficulty of accurately identifying the camouflaged object with complete and fine object structure. To this end, in this paper, we propose a novel boundary-guided network (BGNet) for camouflaged object detection. |
Yujia Sun; Shuo Wang; Chenglizhao Chen; Tian-Zhu Xiang; |
187 | Dynamic Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Unfortunately, there is a lack of training-free mechanism to adjust the model when generalized to the agnostic target domains. To tackle this problem, we develop a brand-new DG variant, namely Dynamic Domain Generalization (DDG), in which the model learns to twist the network parameters to adapt to the data from different domains. |
Zhishu Sun; Zhifeng Shen; Luojun Lin; Yuanlong Yu; Zhifeng Yang; Shicai Yang; Weijie Chen; |
188 | Video Frame Interpolation Based on Deformable Kernel Region Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: These limitations result in that they cannot well adapt to the irregularity of object shape and uncertainty of motion, which may lead to irrelevant reference pixels used for interpolation. In order to solve this problem, we revisit the deformable convolution for video interpolation, which can break the fixed grid restrictions on the kernel region, making the distribution of reference points more suitable for the shape of the object, and thus warp a more accurate interpolation frame. |
Haoyue Tian; Pan Gao; Xiaojiang Peng; |
189 | Hypertron: Explicit Social-Temporal Hypergraph Framework for Multi-Agent Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In addition, most of the existing works model the relation among all agents in a one-to-one manner, which might lead to irrational trajectory predictions due to its redundancy and noise. To address the above issues, we present Hypertron, a human-understandable and lightweight hypergraph-based multi-agent forecasting framework, to explicitly estimate the motions of multiple agents and generate reasonable trajectories. |
Yu Tian; Xingliang Huang; Ruigang Niu; Hongfeng Yu; Peijin Wang; Xian Sun; |
190 | Automatic Recognition of Emotional Subgroups in Images Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work we aim to detect emotional subgroups in images, which can be of great importance for crowd surveillance or event analysis. |
Emmeke Veltmeijer; Charlotte Gerritsen; Koen Hindriks; |
191 | Augmenting Anchors By The Detector Itself Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a novel anchor augmentation method named AADI, which means Augmenting Anchors by the Detector Itself. |
Xiaopei Wan; Guoqiu Li; Yujiu Yang; Zhenhua Guo; |
192 | Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection Via Negative Deterministic Information Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We discover that negative instances (i.e. absolutely wrong instances), ignored in most of the previous studies, normally contain valuable deterministic information. Based on this observation, we here propose a negative deterministic information (NDI) based method for improving WSOD, namely NDI-WSOD. |
Guanchun Wang; Xiangrong Zhang; Zelin Peng; Xu Tang; Huiyu Zhou; Licheng Jiao; |
193 | Iterative Few-shot Semantic Segmentation from Image Label Text Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we focus on a more challenging setting, in which only the image-level labels are available. |
Haohan Wang; Liang Liu; Wuhao Zhang; Jiangning Zhang; Zhenye Gan; Yabiao Wang; Chengjie Wang; Haoqian Wang; |
194 | Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To detect and describe objects in a scene, following the spirit of neural machine translation, we propose a transformer-based encoder-decoder architecture, namely SpaCap3D, to transform objects into descriptions, where we especially investigate the relative spatiality of objects in 3D scenes and design a spatiality-guided encoder via a token-to-token spatial relation learning objective and an object-centric decoder for precise and spatiality-enhanced object caption generation. |
Heng Wang; Chaoyi Zhang; Jianhui Yu; Weidong Cai; |
195 | Adaptive Convolutional Dictionary Network for CT Metal Artifact Reduction Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, most of the existing approaches put less emphasis on modelling and embedding the intrinsic prior knowledge underlying this specific MAR task into their network designs. Against this issue, we propose an adaptive convolutional dictionary network (ACDNet), which leverages both model-based and learning-based methods. |
Hong Wang; Yuexiang Li; Deyu Meng; Yefeng Zheng; |
196 | KUNet: Imaging Knowledge-Inspired Single HDR Image Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, the existing approaches either do not consider constraining solution space or just simply imitate the inverse camera imaging pipeline in stages, without directly formulating the HDR image generation process. In this work, we address this problem by integrating LDR-to-HDR imaging knowledge into an UNet architecture, dubbed as Knowledge-inspired UNet (KUNet). |
Hu Wang; Mao Ye; Xiatian Zhu; Shuai Li; Ce Zhu; Xue Li; |
197 | I2CNet: An Intra- and Inter-Class Context Information Fusion Network for Blastocyst Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose an automatic framework named I2CNet to perform the blastocyst segmentation task in human embryo images. |
Hua Wang; Linwei Qiu; Jingfei Hu; Jicong Zhang; |
198 | PACE: Predictive and Contrastive Embedding for Unsupervised Action Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address those problems,we propose Predictive And Contrastive Embedding (PACE), a unified UAS framework leveraging both predictability and similarity information for more accurate action segmentation. |
Jiahao Wang; Jie Qin; Yunhong Wang; Annan Li; |
199 | Double-Check Soft Teacher for Semi-Supervised Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we revisit the pseudo-labeling based Teacher-Student mutual learning framework for semi-supervised object detection and identify that the inconsistency of the location and feature of the candidate object proposals between the Teacher and the Student branches are the fatal cause of the low quality of the pseudo labels. |
Kuo Wang; Yuxiang Nie; Chaowei Fang; Chengzhi Han; Xuewen Wu; Xiaohui Wang Wang; Liang Lin; Fan Zhou; Guanbin Li; |
200 | RePre: Improving Self-Supervised Vision Transformer with Reconstructive Pre-training Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper incorporates local feature learning into self-supervised vision transformers via Reconstructive Pre-training (RePre). |
Luya Wang; Feng Liang; Yangguang Li; Honggang Zhang; Wanli Ouyang; Jing Shao; |
201 | Uncertainty-Guided Pixel Contrastive Learning for Semi-Supervised Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Due to the lack of expert annotations, however, it is challenging to apply contrastive learning in semi-supervised scenes. To solve this problem, we propose a novel uncertainty-guided pixel contrastive learning method for semi-supervised medical image segmentation. |
Tao Wang; Jianglin Lu; Zhihui Lai; Jiajun Wen; Heng Kong; |
202 | CARD: Semi-supervised Semantic Segmentation Via Class-agnostic Relation Based Denoising Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes that noisy labels can be corrected based on semantic connections among features. |
Xiaoyang Wang; Jimin Xiao; Bingfeng Zhang; Limin Yu; |
203 | Corner Affinity: A Robust Grouping Algorithm to Make Corner-guided Detector Great Again Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel corner grouping algorithm, termed as Corner Affinity, to significantly boost the reliability and robustness of corner grouping. |
Haoran Wei; Chenglong Liu; Ping Guo; Yangguang Zhu; Jiamei Fu; Bing Wang; Peng Wang; |
204 | Multi-scale Spatial Representation Learning Via Recursive Hermite Polynomial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To pursue the two properties, this paper proposes Recursive Hermite Polynomial Networks (RHP-Nets for short). |
Lin (Yuanbo) Wu; Deyin Liu; Xiaojie Guo; Richang Hong; Liangchen Liu; Rui Zhang; |
205 | A Decoder-free Transformer-like Architecture for High-efficiency Single Image Deraining Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we investigate Transformer decoder is not necessary and has huge computational costs. |
Xiao Wu; Ting-Zhu Huang; Liang-Jian Deng; Tian-Jing Zhang; |
206 | Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we introduce a novel backdoor defense framework named Attention Relation Graph Distillation (ARGD), which fully explores the correlation among attention features with different orders using our proposed Attention Relation Graphs (ARGs). |
Jun Xia; Ting Wang; Jiepin Ding; Xian Wei; Mingsong Chen; |
207 | SCMT: Self-Correction Mean Teacher for Semi-supervised Object Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we investigate the causes and effects of noisy pseudo-labels and propose a simple yet effective approach denoted as Self-Correction Mean Teacher(SCMT) to reduce the adverse effects. |
Feng Xiong; Jiayi Tian; Zhihui Hao; Yulin He; Xiaofeng Ren; |
208 | Boosting Multi-Label Image Classification with Complementary Parallel Self-Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this study, we propose a generic framework named Parallel Self-Distillation (PSD) for boosting MLIC models. |
Jiazhi Xu; Sheng Huang; Fengtao Zhou; Luwen Huangfu; Daniel Zeng; Bo Liu; |
209 | Webly-Supervised Fine-Grained Recognition with Partial Label Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: As the label noises significantly hurt the network training, it is desirable to distinguish and eliminate noisy images. In this paper, we propose two strategies, i.e., open-set noise removal and closed-set noise correction, to both remove such two kinds of web noises w.r.t. fine-grained recognition. |
Yu-Yan Xu; Yang Shen; Xiu-Shen Wei; Jian Yang; |
210 | BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Inspired by the success of point-pair features, the goal of this paper is to recover the 6D pose of an object instance segmented from RGB-D images by locally matching pairs of oriented points between the model and camera space. |
Zelin Xu; Yichen Zhang; Ke Chen; Kui Jia; |
211 | Towards Adversarially Robust Deep Image Denoising Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This work systematically investigates the adversarial robustness of deep image denoisers (DIDs), i.e, how well DIDs can recover the ground truth from noisy observations degraded by adversarial perturbations. |
Hanshu Yan; Jingfeng Zhang; Jiashi Feng; Masashi Sugiyama; Vincent Y. F. Tan; |
212 | Weakening The Influence of Clothing: Universal Clothing Attribute Disentanglement for Person Re-Identification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To tackle the challenge of clothes change, we propose a Universal Clothing Attribute Disentanglement network (UCAD) which can effectively weaken the influence of clothing (identity-unrelated) and force the model to learn identity-related features that are unrelated to the worn clothing. |
Yuming Yan; Huimin Yu; Shuzhao Li; Zhaohui Lu; Jianfeng He; Haozhuo Zhang; Runfa Wang; |
213 | Multi-level Consistency Learning for Semi-supervised Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a Multi-level Consistency Learning (MCL) framework for SSDA. |
Zizheng Yan; Yushuang Wu; Guanbin Li; Yipeng Qin; Xiaoguang Han; Shuguang Cui; |
214 | Perceptual Learned Video Compression with Recurrent Conditional GAN Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper proposes a Perceptual Learned Video Compression (PLVC) approach with recurrent conditional GAN. |
Ren Yang; Radu Timofte; Luc Van Gool; |
215 | CrowdFormer: An Overlap Patching Vision Transformer for Top-Down Crowd Counting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, due to the perspective phenomenon, there is a scale variation in real scenes, which causes the density map-based methods suffer from a severe scene generalization problem because only a limited number of scales are fitted in density map prediction and generation. To address this issue, we propose a novel vision transformer network, i.e., CrowdFormer, and a density kernels fusion framework for more accurate density map estimation and generation, respectively. |
Shaopeng Yang; Weiyu Guo; Yuheng Ren; |
216 | Entity-aware and Motion-aware Transformers for Language-driven Action Localization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose entity-aware and motion-aware Transformers that progressively localize actions in videos by first coarsely locating clips with entity queries and then finely predicting exact boundaries in a shrunken temporal region with motion queries. |
Shuo Yang; Xinxiao Wu; |
217 | Learning Prototype Via Placeholder for Zero-shot Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose to learn prototypes via placeholders, termed LPL, to eliminate the domain shift between seen and unseen classes. |
Zaiquan Yang; Yang Liu; Wenjia Xu; Chong Huang; Lei Zhou; Chao Tong; |
218 | Learning Implicit Body Representations from Double Diffusion Based Neural Radiance Fields Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a novel double diffusion based neural radiance field, dubbed DD-NeRF, to reconstruct human body geometry and render the human body appearance in novel views from a sparse set of images. |
Guangming Yao; Hongzhi Wu; Yi Yuan; Lincheng Li; Kun Zhou; Xin Yu; |
219 | RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We introduce a Power-of-Two post-training quantization( PTQ) method for deep neural network that meets hardware requirements and does not call for long-time retraining. |
Hongyi Yao; Pu Li; Jian Cao; Xiangcheng Liu; Chenying Xie; Bingzhang Wang; |
220 | Learning Sparse Interpretable Features For NAS Scoring From Liver Biopsy Images Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a sparse interpretable feature learning method (SparseX) to efficiently estimate NAS scores. |
Chong Yin; Siqi Liu; Vincent Wai-Sun Wong; Pong C Yuen; |
221 | Learning to Hash Naturally Sorts Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This inconsistency in the objectives of training and test may lead to sub-optimal performance since the training loss often fails to reflect the actual retrieval metric. In this paper, we tackle this problem by introducing Naturally-Sorted Hashing (NSH). |
Jiaguo Yu; Yuming Shen; Menghan Wang; Haofeng Zhang; Philip H.S. Torr; |
222 | Multi-Proxy Learning from An Entropy Optimization Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we present an easy-to-implement framework to effectively capture the local neighbor relationships via learning multiple proxies for each class that collectively approximate the intra-class distribution. |
Yunlong Yu; Dingyi Zhang; Yingming Li; Zhongfei Zhang; |
223 | To Fold or Not to Fold: A Necessary and Sufficient Condition on Batch-Normalization Layers Folding Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we demonstrate that the current BN folding approaches are suboptimal in terms of how many layers can be removed. |
Edouard Yvinec; Arnaud Dapogny; Kevin Bailly; |
224 | S2 Transformer for Image Captioning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Their applicability to image captioning is still largely under-explored. Towards this goal, we propose a simple yet effective method, Spatial- and Scale-aware Transformer (S2 Transformer) for image captioning. |
Pengpeng Zeng; Haonan Zhang; Jingkuan Song; Lianli Gao; |
225 | Towards Universal Backward-Compatible Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Despite the success, previous works only investigated a close-set training scenario (i.e., the new training set shares the same classes as the old one), and are limited by more realistic and challenging open-set scenarios. |
Binjie Zhang; Yixiao Ge; Yantao Shen; Shupeng Su; Fanzi Wu; Chun Yuan; Xuyuan Xu; Yexin Wang; Ying Shan; |
226 | Region-level Contrastive and Consistency Learning for Semi-Supervised Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address the issues, we propose a novel region-level contrastive and consistency learning framework (RC^2L) for semi-supervised semantic segmentation. |
Jianrong Zhang; Tianyi Wu; Chuanghao Ding; Hongwei Zhao; Guodong Guo; |
227 | Improving Transferability of Adversarial Examples with Virtual Step and Auxiliary Gradients Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose to improve the transferability of adversarial examples through the use of a virtual step and auxiliary gradients. |
Ming Zhang; Xiaohui Kuang; Hu Li; Zhendong Wu; Yuanping Nie; Gang Zhao; |
228 | Plane Geometry Diagram Parsing Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a powerful diagram parser based on deep learning and graph reasoning. |
Ming-Liang Zhang; Fei Yin; Yi-Han Hao; Cheng-Lin Liu; |
229 | SAR-to-Optical Image Translation Via Neural Partial Differential Equations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Recent researches on SAR-to-optical image translation provide a promising solution and have attracted increasing attentions, though still suffering from low optical image quality with geometric distortion due to the large domain gap. In this paper, we mitigate this issue from a novel perspective, i.e., neural partial differential equations (PDE). |
Mingjin Zhang; Chengyu He; Jing Zhang; Yuxiang Yang; Xiaoqi Peng; Jie Guo; |
230 | A Probabilistic Code Balance Constraint with Compactness and Informativeness Enhancement for Deep Supervised Hashing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, conventional code balance constraints (i.e., bit balance and bit uncorrelation) imposed on avoiding overfitting and improving hash code quality are unsuitable for deep supervised hashing owing to their inefficiency and impracticality of simultaneously learning deep data representations and hash functions. To address this issue, we propose probabilistic code balance constraints on deep supervised hashing to force each hash code to conform to a discrete uniform distribution. |
Qi Zhang; Liang Hu; Longbing Cao; Chongyang Shi; Shoujin Wang; Dora D. Liu; |
231 | CATrans: Context and Affinity Transformer for Few-Shot Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we effectively integrate the context and affinity information via the proposed novel Context and Affinity Transformer (CATrans) in a hierarchical architecture. |
Shan Zhang; Tianyi Wu; Sitong Wu; Guodong Guo; |
232 | Few-Shot Adaptation of Pre-Trained Networks for Domain Shift Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose a framework for few-shot domain adaptation to address the practical challenges of data-efficient adaptation. |
Wenyu Zhang; Li Shen; Wanyue Zhang; Chuan-Sheng Foo; |
233 | Enhancing The Transferability of Adversarial Examples with Random Patch Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes the Random Patch Attack (RPA) to significantly improve the transferability of adversarial examples by the patch-wise random transformation that effectively highlights important intrinsic features of objects. |
Yaoyuan Zhang; Yu-an Tan; Tian Chen; Xinrui Liu; Quanxin Zhang; Yuanzhang Li; |
234 | Visual Emotion Representation Learning Via Emotion-Aware Pre-training Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a large-scale multimodal pre-training method to learn visual emotion representation by aligning emotion, object, attribute triplet with a contrastive loss. |
Yue Zhang; Wanying Ding; Ran Xu; Xiaohua Hu; |
235 | Distilling Inter-Class Distance for Semantic Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The previous knowledge distillation methods for semantic segmentation focus on pixel-wise feature alignment and intra-class feature variation distillation, neglecting to transfer the knowledge of the inter-class distance in the feature space, which is important for semantic segmentation such a pixel-wise classification task. To address this issue, we propose an Inter-class Distance Distillation (IDD) method to transfer the inter-class distance in the feature space from the teacher network to the student network. |
Zhengbo Zhang; Chunluan Zhou; Zhigang Tu; |
236 | Domain Adversarial Learning for Color Constancy Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Though contemporary approaches based on convolutional neural networks significantly improve illuminant estimation, they suffer from the seriously insufficient data problem. To solve this problem by effectively utilizing multi-domain data, we propose the Domain Adversarial Learning Color Constancy (DALCC) which consists of the Domain Adversarial Learning Branch (DALB) and the Feature Reweighting Module (FRM). |
Zhifeng Zhang; Xuejing Kang; Anlong Ming; |
237 | Domain Adaptation Via Maximizing Surrogate Mutual Information Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose a novel framework called SIDA (Surrogate Mutual Information Maximization Domain Adaptation) with strong theoretical guarantees. |
Haiteng Zhao; Chang Ma; Qinyu Chen; Zhi-Hong Deng; |
238 | C3-STISR: Scene Text Image Super-resolution with Triple Clues Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we present a novel method C3-STISR that jointly exploits the recognizer’s feedback, visual and linguistical information as clues to guide super-resolution. |
Minyi Zhao; Miao Wang; Fan Bai; Bingjia Li; Jie Wang; Shuigeng Zhou; |
239 | Learning to Generate Image Source-Agnostic Universal Adversarial Perturbations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: A “universal adversarial perturbation” (UAP) can simultaneously attack multiple images, and thus offers a more unified threat model, obviating an image-wise attack algorithm. |
Pu Zhao; Parikshit Ram; Songtao Lu; Yuguang Yao; Djallel Bouneffouf; Xue Lin; Sijia Liu; |
240 | Test-time Fourier Style Calibration for Domain Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To solve the dilemma of having no access to the target domain during training, we introduce Test-time Fourier Style Calibration (TF-Cal) for calibrating the target domain style on the fly during testing. |
Xingchen Zhao; Chang Liu; Anthony Sicilia; Seong Jae Hwang; Yun Fu; |
241 | Visual Similarity Attention Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: While there has been substantial progress in learning suitable distance metrics, these techniques in general lack transparency and decision reasoning, i.e., explaining why the input set of images is similar or dissimilar. In this work, we solve this key problem by proposing the first method to generate generic visual similarity explanations with gradient-based attention. |
Meng Zheng; Srikrishna Karanam; Terrence Chen; Richard J. Radke; Ziyan Wu; |
242 | Imperceptible Backdoor Attack: From Input Space to Feature Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we analyze the drawbacks of existing attack approaches and propose a novel imperceptible backdoor attack. |
Nan Zhong; Zhenxing Qian; Xinpeng Zhang; |
243 | Rainy WCity: A Real Rainfall Dataset with Diverse Conditions for Semantic Driving Scene Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Scene understanding in adverse weather conditions (e.g. rainy and foggy days) has drawn increasing attention, arising some specific benchmarks and algorithms. However, scene … |
Xian Zhong; Shidong Tu; Xianzheng Ma; Kui Jiang; Wenxin Huang; Zheng Wang; |
244 | HifiHead: One-Shot High Fidelity Neural Head Synthesis with 3D Control Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose HifiHead, a high fidelity neural talking head synthesis method, which can well preserve the source image’s appearance and control the motion (e.g., pose, expression, gaze) flexibly with 3D morphable face models (3DMMs) parameters derived from a driving image or indicated by users. |
Feida Zhu; Junwei Zhu; Wenqing Chu; Ying Tai; Zhifeng Xie; Xiaoming Huang; Chengjie Wang; |
245 | Hierarchical Bilevel Learning with Architecture and Loss Search for Hadamard-based Image Restoration Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This way brings about expensive verification costs for seeking out the optimal solution. |
Guijing Zhu; Long Ma; Xin Fan; Risheng Liu; |
246 | A Solver + Gradient Descent Training Algorithm for Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a novel hybrid algorithm for training Deep Neural Networks that combines the state-of-the-art Gradient Descent (GD) method with a Mixed Integer Linear Programming (MILP) solver, outperforming GD and variants in terms of accuracy, as well as resource and data efficiency for both regression and classification tasks. |
Dhananjay Ashok; Vineel Nagisetty; Christopher Srinivasa; Vijay Ganesh; |
247 | Fine-grained Complexity of Partial Minimum Satisfiability Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our goal is to fix the issue and show a O*((2-ɛ)^m) lower bound under the SETH assumption (here m is the total number of clauses), as well as several other lower bounds and parameterized exact algorithms with better-than-trivial running time. |
Ivan Bliznets; Danil Sagunov; Kirill Simonov; |
248 | QCDCL with Cube Learning or Pure Literal Elimination – What Is Best? Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We formalise and investigate several versions of QCDCL that include cube learning and/or pure-literal elimination, and formally compare the resulting solving models via proof complexity techniques. |
Benjamin Böhm; Tomáš Peitl; Olaf Beyersdorff; |
249 | Combining Constraint Solving and Bayesian Techniques for System Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we present a combination of Bayesian optimization and SMT-based constraint solving to achieve safe and stable solutions with optimality guarantees. |
Franz Brauße; Zurab Khasidashvili; Konstantin Korovin; |
250 | DPSampler: Exact Weighted Sampling Using Dynamic Programming Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Recent work in the closely connected field of model counting, however, has shown that smartly composing different subformulas using dynamic programming and Algebraic Decision Diagrams (ADDs) can outperform d-DNNF-style approaches on many benchmarks. In this work, we present a modular algorithm called DPSampler that extends such dynamic-programming techniques to the problem of exact weighted sampling. |
Jeffrey M. Dudek; Aditya A. Shrotri; Moshe Y. Vardi; |
251 | A Multivariate Complexity Analysis of Qualitative Reasoning Problems Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we consider single-exponential algorithms via a multivariate analysis consisting of a fine-grained parameter n (e.g., the number of variables) and a coarse-grained parameter k expected to be relatively small. |
Leif Eriksson; Victor Lagerkvist; |
252 | Accelerated Multiplicative Weights Update Avoids Saddle Points Almost Always Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Despite it has been known that MWU avoids saddle points, there is a question that remains unaddressed: “Is there an accelerated version of MWU that avoids saddle points provably?” In this paper we provide a positive answer to above question. |
Yi Feng; Ioannis Panageas; Xiao Wang; |
253 | Large Neighbourhood Search for Anytime MaxSAT Solving Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a method for applying LNS to improve anytime maximum satisfiability (MaxSAT) solving by introducing a neighbourhood selection policy that shows good empirical performance. |
Randy Hickey; Fahiem Bacchus; |
254 | Online Matching with Controllable Rewards and Arrival Probabilities Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this study, we formulate a new optimization problem, Online Matching with Controllable Rewards and Arrival probabilities (OM-CRA), to simultaneously determine not only the matching strategy but also the rewards and arrival probabilities. |
Yuya Hikima; Yasunori Akagi; Naoki Marumo; Hideaki Kim; |
255 | Encoding Probabilistic Graphical Models Into Stochastic Boolean Satisfiability Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we exploit SSAT solvers for the inference of Probabilistic Graphical Models (PGMs), an essential representation for probabilistic reasoning. |
Cheng-Han Hsieh; Jie-Hong R. Jiang; |
256 | Degradation Accordant Plug-and-Play for Low-Rank Tensor Completion Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This work proposes a novel low-rank tensor completion model, in which the inherent low-rank prior and external degradation accordant data-driven prior are simultaneously utilized. |
Yexun Hu; Tai-Xiang Jiang; Xi-Le Zhao; |
257 | Using Constraint Programming and Graph Representation Learning for Generating Interpretable Cloud Security Policies Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We identify reducing dormant permissions of cloud users as an optimality criterion, which intuitively implies minimizing unnecessary datastore access permissions. |
Mikhail Kazdagli; Mohit Tiwari; Akshat Kumar; |
258 | Best Heuristic Identification for Constraint Satisfaction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this study, we propose an adaptive variant of Successive Halving that exploits Luby’s universal restart sequence. |
Frederic Koriche; Christophe Lecoutre; Anastasia Paparrizou; Hugues Wattez; |
259 | AllSATCC: Boosting AllSAT Solving with Efficient Component Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, observing that the lack of component analysis may result in more work for algorithms with non-chronological backtracking, we propose a DPLL-based algorithm for solving AllSAT problem, named AllSATCC, which takes advantage of component analysis to reduce work repetition caused by non-chronological backtracking. |
Jiaxin Liang; Feifei Ma; Junping Zhou; Minghao Yin; |
260 | Automated Program Analysis: Revisiting Precondition Inference Through Constraint Acquisition Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we explore how Constraint Acquisition (CA), a learning framework from Constraint Programming, can be leveraged to automatically infer program preconditions in a black-box manner, from input-output observations. |
Grégoire Menguy; Sébastien Bardin; Nadjib Lazaar; Arnaud Gotlieb; |
261 | Threshold-free Pattern Mining Meets Multi-Objective Optimization: Application to Association Rules Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce a new model for efficiently mining Pareto optimal patterns with constraint programming. |
Charles Vernerey; Samir Loudni; Noureddine Aribi; Yahia Lebbah; |
262 | An Exact MaxSAT Algorithm: Further Observations and Further Improvements Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we further improve the result to O*(1.2886^m). By using some new reduction and branching techniques we can avoid several bottlenecks in previous algorithms and get the improvement on this important problem. |
Mingyu Xiao; |
263 | Inverting 43-step MD4 Via Cube-and-Conquer Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this study, 40-, 41-, 42-, and 43-step versions of MD4 are successfully inverted. |
Oleg Zaikin; |
264 | BandMaxSAT: A Local Search MaxSAT Solver with Multi-armed Bandit Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We address Partial MaxSAT (PMS) and Weighted PMS (WPMS), two practical generalizations of the MaxSAT problem, and propose a local search algorithm called BandMaxSAT, that applies a multi-armed bandit to guide the search direction, for these problems. |
Jiongzhi Zheng; Kun He; Jianrong Zhou; Yan Jin; Chu-Min Li; Felip Manyà; |
265 | A Strengthened Branch and Bound Algorithm for The Maximum Common (Connected) Subgraph Problem Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a new and strengthened Branch-and-Bound (BnB) algorithm for the maximum common (connected) induced subgraph problem based on two new operators, Long-Short Memory (LSM) and Leaf vertex Union Match (LUM). |
Jianrong Zhou; Kun He; Jiongzhi Zheng; Chu-Min Li; Yanli Liu; |
266 | Doubly Sparse Asynchronous Learning for Stochastic Composite Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address the challenges, we propose a new accelerated doubly sparse asynchronous learning (DSAL) method for stochastic composite optimization, under which two algorithms are proposed on shared-memory and distributed-memory architecture respectively, which only conducts gradient descent on the nonzero coordinates (data sparsity) and active set (model sparsity). |
Runxue Bao; Xidong Wu; Wenhan Xian; Heng Huang; |
267 | Hypergraph Structure Learning for Hypergraph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a Hypergraph Structure Learning (HSL) framework, which optimizes the hypergraph structure and the HGNNs simultaneously in an end-to-end way. |
Derun Cai; Moxian Song; Chenxi Sun; Baofeng Zhang; Shenda Hong; Hongyan Li; |
268 | Entity Alignment with Reliable Path Reasoning and Relation-aware Heterogeneous Graph Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a more effective entity alignment framework, RPR-RHGT, which integrates relation and path structure information, as well as the heterogeneous information in KGs. |
Weishan Cai; Wenjun Ma; Jieyu Zhan; Yuncheng Jiang; |
269 | Non-Euclidean Self-Organizing Maps Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present the generalized setup for non-Euclidean SOMs. |
Dorota Celińska-Kopczyńska; Eryk Kopczyński; |
270 | Can Abnormality Be Detected By Graph Neural Networks? Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: A natural and fundamental question that arises here is: can abnormality be detected by graph neural networks? In this paper, we aim to answer this question, which is nontrivial. |
Ziwei Chai; Siqi You; Yang Yang; Shiliang Pu; Jiarong Xu; Haoyang Cai; Weihao Jiang; |
271 | Robust High-Dimensional Classification From Few Positive Examples Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We tackle an extreme form of imbalanced classification, with up to 105 features but as few as 5 samples from the minority class. |
Deepayan Chakrabarti; Benjamin Fauber; |
272 | Vertically Federated Graph Neural Network for Privacy-Preserving Node Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, such information could possibly be isolated by different data holders in practice, which is the so-called data isolation problem. To solve this problem, in this paper, we propose VFGNN, a federated GNN learning paradigm for privacy-preserving node classification task under data vertically partitioned setting, which can be generalized to existing GNN models. |
Chaochao Chen; Jun Zhou; Longfei Zheng; Huiwen Wu; Lingjuan Lyu; Jia Wu; Bingzhe Wu; Ziqi Liu; Li Wang; Xiaolin Zheng; |
273 | Meta-Learning Based Knowledge Extrapolation for Knowledge Graphs in The Federated Setting Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this problem, a model trained on an existing KG needs to embed an emerging KG with unseen entities and relations. To solve this problem, we introduce the meta-learning setting, where a set of tasks are sampled on the existing KG to mimic the link prediction task on the emerging KG. |
Mingyang Chen; Wen Zhang; Zhen Yao; Xiangnan Chen; Mengxiao Ding; Fei Huang; Huajun Chen; |
274 | Mutual Distillation Learning Network for Trajectory-User Linking Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a novel Mutual distillation learning network to solve the TUL problem for sparse check-in mobility data, named MainTUL. |
Wei Chen; ShuZhe Li; Chao Huang; Yanwei Yu; Yongguo Jiang; Junyu Dong; |
275 | Towards Robust Dense Retrieval Via Local Ranking Alignment Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Herein, we argue that it would be beneficial to allow the DR model to learn to align the relative positions of query-passage pairs in the representation space, as query variations cause the query vector to drift away from its original position, affecting the subsequent DR effectiveness. To this end, we propose RoDR, a novel robust DR model that learns to calibrate the in-batch local ranking of query variation to that of original query for the DR space alignment. |
Xuanang Chen; Jian Luo; Ben He; Le Sun; Yingfei Sun; |
276 | Filtration-Enhanced Graph Transformation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To break the 1-WL expressiveness barrier, we propose a novel method called filtration-enhanced graph transformation, which is based on a concept from the area of topological data analysis. |
Zijian Chen; Rong-Hua Li; Hongchao Qin; Huanzhong Duan; Yanxiong Lu; Qiangqiang Dai; Guoren Wang; |
277 | Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: (ii) Variable-specific parameters: we propose a light-weight method to enable distinct sets of model parameters for different variables’ time series to enhance accuracy without compromising efficiency and memory usage. |
Razvan-Gabriel Cirstea; Chenjuan Guo; Bin Yang; Tung Kieu; Xuanyi Dong; Shirui Pan; |
278 | CADET: Calibrated Anomaly Detection for Mitigating Hardness Bias Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we empirically show the significance of this hardness bias present in a range of recent deep anomaly detection methods. To mitigate this, we propose an efficient and plug-and-play error calibration method which mitigates this hardness bias in the anomaly scoring without the need to retrain the model. |
Ailin Deng; Adam Goodge; Lang Yi Ang; Bryan Hooi; |
279 | Private Semi-Supervised Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we design an effective federated semi-supervised learning framework (FedSSL) to fully leverage both labeled and unlabeled data sources. |
Chenyou Fan; Junjie Hu; Jianwei Huang; |
280 | Feature and Instance Joint Selection: A Reinforcement Learning Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, such selections have mostly been studied separately, while existing work towards the joint selection conducts feature/instance selection coarsely; thus neglecting the latent fine-grained interaction between feature space and instance space. To address this challenge, we propose a reinforcement learning solution to accomplish the joint selection task and simultaneously capture the interaction between the selection of each feature and each instance. |
Wei Fan; Kunpeng Liu; Hao Liu; Hengshu Zhu; Hui Xiong; Yanjie Fu; |
281 | MetaER-TTE: An Adaptive Meta-learning Model for En Route Travel Time Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Since trajectories with different contextual information tend to have different characteristics, the existing meta-learning method for ER-TTE cannot fit each trajectory well because it uses the same model for all trajectories. To this end, we propose a novel adaptive meta-learning model called MetaER-TTE. |
Yu Fan; Jiajie Xu; Rui Zhou; Jianxin Li; Kai Zheng; Lu Chen; Chengfei Liu; |
282 | When Transfer Learning Meets Cross-City Urban Flow Prediction: Spatio-Temporal Adaptation Matters Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a novel Spatio-Temporal Adaptation Network (STAN) to perform urban flow prediction for data-scarce cities via the spatio-temporal knowledge transferred from data-rich cities. |
Ziquan Fang; Dongen Wu; Lu Pan; Lu Chen; Yunjun Gao; |
283 | Disentangling The Computational Complexity of Network Untangling Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we initiate a multivariate complexity analysis involving the following parameters: number of vertices, lifetime of the temporal graph, number of intervals per vertex, and the interval length bound. |
Vincent Froese; Pascal Kunz; Philipp Zschoche; |
284 | Modeling Precursors for Temporal Knowledge Graph Reasoning Via Auto-encoder Structure Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a novel auto-encoder architecture that introduces a relation-aware graph attention layer into transformer (rGalT) to accommodate inference over the TKG. |
Yifu Gao; Linhui Feng; Zhigang Kan; Yi Han; Linbo Qiao; Dongsheng Li; |
285 | Self-supervised Graph Neural Networks for Multi-behavior Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel self-supervised graph collaborative filtering model for multi-behavior recommendation named S-MBRec. |
Shuyun Gu; Xiao Wang; Chuan Shi; Ding Xiao; |
286 | Constrained Adaptive Projection with Pretrained Features for Anomaly Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose an anomaly detection framework called constrained adaptive projection with pretrained features (CAP). |
Xingtai Gui; Di Wu; Yang Chang; Shicai Fan; |
287 | Quaternion Ordinal Embedding Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, most of the existing methods merely focus on b). To address this issue, our goal in this paper is to seek a generic OE method to embrace the two features simultaneously. |
Wenzheng Hou; Qianqian Xu; Ke Ma; Qianxiu Hao; Qingming Huang; |
288 | MERIT: Learning Multi-level Representations on Temporal Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Despite effectiveness, these methods commonly ignore the individual- and combinatorial-level patterns derived from different types of interactions (e.g.,user-item), which are at the heart of the representation learning on temporal graphs. To fill this gap, we propose MERIT, a novel multi-level graph attention network for inductive representation learning on temporal graphs.We adaptively embed the original timestamps to a higher, continuous dimensional space for learn-ing individual-level periodicity through Personalized Time Encoding (PTE) module. |
Binbin Hu; Zhengwei Wu; Jun Zhou; Ziqi Liu; Zhigang Huangfu; Zhiqiang Zhang; Chaochao Chen; |
289 | GraphDIVE: Graph Classification By Mixture of Diverse Experts Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To boost the performance of GNNs and investigate the relationship between topological structure and class imbalance, we propose GraphDIVE, which learns multi-view graph representations and combine multi-view experts (i.e., classifiers). |
Fenyu Hu; Liping Wang; Qiang Liu; Shu Wu; Liang Wang; Tieniu Tan; |
290 | End-to-End Open-Set Semi-Supervised Node Classification with Out-of-Distribution Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we study a novel problem of end-to-end open-set semi-supervised node classification (OSSNC) on graphs, which deals with node classification in the presence of OOD nodes. |
Tiancheng Huang; Donglin Wang; Yuan Fang; Zhengyu Chen; |
291 | A Sparse-Motif Ensemble Graph Convolutional Network Against Over-smoothing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper believes that the main cause lies in the limited diversity along the message passing pipeline. Inspired by this, we propose a Sparse-Motif Ensemble Graph Convolutional Network (SMEGCN). |
Xuan Jiang; Zhiyong Yang; Peisong Wen; Li Su; Qingming Huang; |
292 | CGMN: A Contrastive Graph Matching Network for Self-Supervised Graph Similarity Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In addition, existing unsupervised graph similarity learning methods are mainly clustering-based, which ignores the valuable information embodied in graph pairs. To this end, we propose a contrastive graph matching network (CGMN) for self-supervised graph similarity learning in order to calculate the similarity between any two input graph objects. |
Di Jin; Luzhi Wang; Yizhen Zheng; Xiang Li; Fei Jiang; Wei Lin; Shirui Pan; |
293 | RAW-GNN: RAndom Walk Aggregation Based Graph Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Here, we introduce a novel aggregation mechanism and develop a RAndom Walk Aggregation-based Graph Neural Network (called RAW-GNN) method. |
Di Jin; Rui Wang; Meng Ge; Dongxiao He; Xiang Li; Wei Lin; Weixiong Zhang; |
294 | Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: With privacy concerns, accessing the decentralized data is limited to either individual clients or different silos. To tackle these issues, we propose a privacy-preserving framework to analyze the GW discrepancy of node embedding learned locally from graph neural networks in a federated flavor, and then explicitly place local differential privacy (LDP) based on Multi-bit Encoder to protect sensitive information. |
Hongwei Jin; Xun Chen; |
295 | TGNN: A Joint Semi-supervised Framework for Graph-level Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We address the challenge by proposing a novel semi-supervised framework called Twin Graph Neural Network (TGNN). |
Wei Ju; Xiao Luo; Meng Qu; Yifan Wang; Chong Chen; Minghua Deng; Xian-Sheng Hua; Ming Zhang; |
296 | HashNWalk: Hash and Random Walk Based Anomaly Detection in Hyperedge Streams Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose HashNWalk, an incremental algorithm that detects anomalies in a stream of hyperedges. |
Geon Lee; Minyoung Choe; Kijung Shin; |
297 | MLP4Rec: A Pure MLP Architecture for Sequential Recommendations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a novel sequential recommender system (MLP4Rec) based on the recent advances of MLP-based architectures, which is naturally sensitive to the order of items in a sequence. |
Muyang Li; Xiangyu Zhao; Chuan Lyu; Minghao Zhao; Runze Wu; Ruocheng Guo; |
298 | Community Question Answering Entity Linking Via Leveraging Auxiliary Data Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we define a new task of CQA entity linking (CQAEL) as linking the textual entity mentions detected from CQA texts with their corresponding entities in a knowledge base. |
Yuhan Li; Wei Shen; Jianbo Gao; Yadong Wang; |
299 | TiRGN: Time-Guided Recurrent Graph Network with Local-Global Historical Patterns for Temporal Knowledge Graph Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: From the perspective of historical development laws, comprehensively considering the sequential, repetitive, and cyclical patterns of historical facts is conducive to predicting future facts. To this end, we propose a novel representation learning model for TKG reasoning, namely TiRGN, a time-guided recurrent graph network with local-global historical patterns. |
Yujia Li; Shiliang Sun; Jing Zhao; |
300 | Discrete Listwise Personalized Ranking for Fast Top-N Recommendation with Implicit Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, current hashing methods for top-N recommendation fail to align their learning objectives (such as pointwise or pairwise loss) with the benchmark metrics for ranking quality (e.g. Average Precision, AP), resulting in sub-optimal accuracy. To this end, we propose a Discrete Listwise Personalized Ranking (DLPR) model that optimizes AP under discrete constraints for fast and accurate top-N recommendation. |
Fangyuan Luo; Jun Wu; Tao Wang; |
301 | Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose APPLE, a personalized cross-silo FL framework that adaptively learns how much each client can benefit from other clients’ models. |
Jun Luo; Shandong Wu; |
302 | Reconciling Cognitive Modeling with Knowledge Forgetting: A Continuous Time-aware Neural Network Approach Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: While considerable efforts have been made in this direction, a long-standing research challenge is how to naturally integrate the forgetting mechanism into the learning process of knowledge concepts. To this end, in this paper, we propose a novel Continuous Time based Neural Cognitive Modeling(CT-NCM) approach to integrate the dynamism and continuity of knowledge forgetting into students’ learning process modeling in a realistic manner. |
Haiping Ma; Jingyuan Wang; Hengshu Zhu; Xin Xia; Haifeng Zhang; Xingyi Zhang; Lei Zhang; |
303 | Continual Federated Learning Based on Knowledge Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose Continual Federated Learning with Distillation (CFeD) to address catastrophic forgetting under FL. |
Yuhang Ma; Zhongle Xie; Jue Wang; Ke Chen; Lidan Shou; |
304 | Physics-Informed Long-Sequence Forecasting From Multi-Resolution Spatiotemporal Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose Spatiotemporal Koopman Multi-Resolution Network (ST-KMRN), a physics-informed learning framework for long-sequence forecasting from multi-resolution spatiotemporal data. |
Chuizheng Meng; Hao Niu; Guillaume Habault; Roberto Legaspi; Shinya Wada; Chihiro Ono; Yan Liu; |
305 | Raising The Bar in Graph-level Anomaly Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: By drawing on ideas from self-supervised learning and transformation learning, we present a new deep learning approach that significantly improves existing deep one-class approaches by fixing some of their known problems, including hypersphere collapse and performance flip. |
Chen Qiu; Marius Kloft; Stephan Mandt; Maja Rudolph; |
306 | Poisoning Deep Learning Based Recommender Model in Federated Learning Scenarios Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Various attack methods against recommender systems have been proposed in the past years, and the security issues of recommender systems have drawn considerable attention. |
Dazhong Rong; Qinming He; Jianhai Chen; |
307 | Towards Resolving Propensity Contradiction in Offline Recommender Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This leads to a critical self-contradiction; IPS is ineffective without MCAR data, even though it originally aims to learn recommenders from only missing-not-at-random feedback. To resolve this propensity contradiction, we derive a propensity-independent generalization error bound and propose a novel algorithm to minimize the theoretical bound via adversarial learning. |
Yuta Saito; Masahiro Nomura; |
308 | Federated Learning on Heterogeneous and Long-Tailed Data Via Classifier Re-Training with Federated Features Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we reveal an intriguing fact that the biased classifier is the primary factor leading to the poor performance of the global model. |
Xinyi Shang; Yang Lu; Gang Huang; Hanzi Wang; |
309 | Long-term Spatio-Temporal Forecasting Via Dynamic Multiple-Graph Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To aggregate the information across multiple graphs, we propose a new dynamic multi-graph fusion module to characterize the correlations of nodes within a graph and the nodes across graphs via the spatial attention and graph attention mechanisms. |
Wei Shao; Zhiling Jin; Shuo Wang; Yufan Kang; Xiao Xiao; Hamid Menouar; Zhaofeng Zhang; Junshan Zhang; Flora Salim; |
310 | Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we shed light on the path level patterns in graphs that can explicitly reflect rich semantic and structural information. |
Yifei Sun; Haoran Deng; Yang Yang; Chunping Wang; Jiarong Xu; Renhong Huang; Linfeng Cao; Yang Wang; Lei Chen; |
311 | Personalized Federated Learning with Contextualized Generalization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel concept called contextualized generalization (CG) to provide each client with fine-grained context knowledge that can better fit the local data distributions and facilitate faster model convergence, based on which we properly design a framework of PFL, dubbed CGPFL. |
Xueyang Tang; Song Guo; Jingcai Guo; |
312 | Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, existing KGC methods suffer from two main issues, 1) the false negative issue, i.e., the sampled negative training instances may include potential true facts; and 2) the data sparsity issue, i.e., true facts account for only a tiny part of all possible facts. To this end, we propose positive-unlabeled learning with adversarial data augmentation (PUDA) for KGC. |
Zhenwei Tang; Shichao Pei; Zhao Zhang; Yongchun Zhu; Fuzhen Zhuang; Robert Hoehndorf; Xiangliang Zhang; |
313 | Anomaly Detection By Leveraging Incomplete Anomalous Knowledge with Anomaly-Aware Bidirectional GANs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: The goal of anomaly detection is to identify anomalous samples from normal ones. In this paper, a small number of anomalies are assumed to be available at the training stage, but they are assumed to be collected only from several anomaly types, leaving the majority of anomaly types not represented in the collected anomaly dataset at all. |
Bowen Tian; Qinliang Su; Jian Yin; |
314 | MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, MEI has several drawbacks, some of which carried from its subsumed tensor-decomposition-based models. In this paper, we address these drawbacks and introduce the Multi-partition Embedding Interaction iMproved beyond block term format (MEIM) model, with independent core tensor for ensemble effects and soft orthogonality for max-rank mapping, in addition to multi-partition embedding. |
Hung-Nghiep Tran; Atsuhiro Takasu; |
315 | HCFRec: Hash Collaborative Filtering Via Normalized Flow with Structural Consensus for Efficient Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, Hash-CF often faces two challenging problems, i.e., optimization on discrete representations and preserving semantic information in learned representations. To address the above two challenges, we propose HCFRec, a novel Hash-CF approach for effective and efficient recommendations. |
Fan Wang; Weiming Liu; Chaochao Chen; Mengying Zhu; Xiaolin Zheng; |
316 | Augmenting Knowledge Graphs for Better Link Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Recent methods propose to enhance the loss function with a literal-aware term. In this paper, we propose KGA: a knowledge graph augmentation method that incorporates literals in an embedding model without modifying its loss function. |
Jiang Wang; Filip Ilievski; Pedro Szekely; Ke-Thia Yao; |
317 | FAITH: Few-Shot Graph Classification with Hierarchical Task Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: On the other hand, it remains non-trivial to utilize task correlations due to the complex components in a large number of meta-training tasks. To deal with this, we propose a novel few-shot learning framework FAITH that captures task correlations via constructing a hierarchical task graph at different granularities. |
Song Wang; Yushun Dong; Xiao Huang; Chen Chen; Jundong Li; |
318 | Language Models As Knowledge Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose LMKE, which adopts Language Models to derive Knowledge Embeddings, aiming at both enriching representations of long-tail entities and solving problems of prior description-based methods. |
Xintao Wang; Qianyu He; Jiaqing Liang; Yanghua Xiao; |
319 | Ensemble Multi-Relational Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: It is well established that graph neural networks (GNNs) can be interpreted and designed from the perspective of optimization objective. |
Yuling Wang; Hao Xu; Yanhua Yu; Mengdi Zhang; Zhenhao Li; Yuji Yang; Wei Wu; |
320 | CTL-MTNet: A Novel CapsNet and Transfer Learning-Based Mixed Task Net for Single-Corpus and Cross-Corpus Speech Emotion Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: An essential challenge in SER is to extract common attributes from different speakers or languages, especially when a specific source corpus has to be trained to recognize the unknown data coming from another speech corpus. To address this challenge, a Capsule Network (CapsNet) and Transfer Learning based Mixed Task Net (CTL-MTNet) are proposed to deal with both the single-corpus and cross-corpus SER tasks simultaneously in this paper. |
Xin-Cheng Wen; JiaXin Ye; Yan Luo; Yong Xu; Xuan-Ze Wang; Chang-Li Wu; Kun-Hong Liu; |
321 | Multi-Graph Fusion Networks for Urban Region Embedding Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose multi-graph fusion networks (MGFN) to enable the cross domain prediction tasks. |
Shangbin Wu; Xu Yan; Xiaoliang Fan; Shirui Pan; Shichao Zhu; Chuanpan Zheng; Ming Cheng; Cheng Wang; |
322 | Understanding and Mitigating Data Contamination in Deep Anomaly Detection: A Kernel-based Approach Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we study the performance of the anomaly detectors under data contamination and construct a data-efficient countermeasure against data contamination. |
Shuang Wu; Jingyu Zhao; Guangjian Tian; |
323 | Decentralized Unsupervised Learning of Visual Representations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, the distributed data collected on clients are usually not independent and identically distributed (non-IID) among clients, and each client may only have few classes of data, which degrades the performance of CL and learned representations. To tackle this problem, we propose a collaborative contrastive learning framework consisting of two approaches: feature fusion and neighborhood matching, by which a unified feature space among clients is learned for better data representations. |
Yawen Wu; Zhepeng Wang; Dewen Zeng; Meng Li; Yiyu Shi; Jingtong Hu; |
324 | FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose FEDCG, a novel federated learning method that leverages conditional generative adversarial networks to achieve high-level privacy protection while still maintaining competitive model performance. |
Yuezhou Wu; Yan Kang; Jiahuan Luo; Yuanqin He; Lixin Fan; Rong Pan; Qiang Yang; |
325 | Subgraph Neighboring Relations Infomax for Inductive Link Prediction on Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To address that, we propose Subgraph Neighboring Relations Infomax, SNRI, which sufficiently exploits complete neighboring relations from two aspects: neighboring relational feature for node feature and neighboring relational path for sparse subgraph. |
Xiaohan Xu; Peng Zhang; Yongquan He; Chengpeng Chao; Chaoyang Yan; |
326 | GOCPT: Generalized Online Canonical Polyadic Tensor Factorization and Completion Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Existing methods cannot support such complex scenarios. To fill the gap, this paper proposes a Generalized Online Canonical Polyadic (CP) Tensor factorization and completion framework (named GOCPT) for this general setting, where we maintain the CP structure of such dynamic tensors during the evolution. |
Chaoqi Yang; Cheng Qian; Jimeng Sun; |
327 | Trading Hard Negatives and True Negatives: A Debiased Contrastive Collaborative Filtering Approach Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We devise a new approach named as Hardness-Aware Debiased Contrastive Collaborative Filtering (HDCCF) to resolve the dilemma. |
Chenxiao Yang; Qitian Wu; Jipeng Jin; Xiaofeng Gao; Junwei Pan; Guihai Chen; |
328 | Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose Regularized Graph Structure Learning (RGSL) model to incorporate both explicit prior structure and implicit structure together, and learn the forecasting deep networks along with the graph structure. |
Hongyuan Yu; Ting Li; Weichen Yu; Jianguo Li; Yan Huang; Liang Wang; Alex Liu; |
329 | CERT: Continual Pre-training on Sketches for Library-oriented Code Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we investigate how to leverage an unlabelled code corpus to train a model for library-oriented code generation. |
Daoguang Zan; Bei Chen; Dejian Yang; Zeqi Lin; Minsu Kim; Bei Guan; Yongji Wang; Weizhu Chen; Jian-Guang Lou; |
330 | Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a self-supervised learning framework that jointly optimizes a multi-view contrastive learning-based module and an attribute reconstruction-based module to more accurately detect anomalies on attributed networks. |
Jiaqiang Zhang; Senzhang Wang; Songcan Chen; |
331 | Dynamic Graph Learning Based on Hierarchical Memory for Origin-Destination Demand Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Recent years have witnessed a rapid growth of applying deep spatiotemporal methods in traffic forecasting. |
Ruixing Zhang; Liangzhe Han; Boyi Liu; Jiayuan Zeng; Leilei Sun; |
332 | GRELEN: Multivariate Time Series Anomaly Detection from The Perspective of Graph Relational Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel Graph Relational Learning Network (GReLeN) to detect multivariate time series anomalies from the perspective of between-sensor dependence relationship learning. |
Weiqi Zhang; Chen Zhang; Fugee Tsung; |
333 | Enhancing Sequential Recommendation with Graph Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a novel recommendation framework, namely Graph Contrastive Learning for Sequential Recommendation (GCL4SR). |
Yixin Zhang; Yong Liu; Yonghui Xu; Hao Xiong; Chenyi Lei; Wei He; Lizhen Cui; Chunyan Miao; |
334 | T-SMOTE: Temporal-oriented Synthetic Minority Oversampling Technique for Imbalanced Time Series Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, to address the class imbalance problem, we propose a novel and practical oversampling method named T-SMOTE, which can make full use of the temporal information of time-series data. |
Pu Zhao; Chuan Luo; Bo Qiao; Lu Wang; Saravan Rajmohan; Qingwei Lin; Dongmei Zhang; |
335 | MFAN: Multi-modal Feature-enhanced Attention Networks for Rumor Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose a novel Multi-modal Feature-enhanced Attention Networks (MFAN) for rumor detection, which makes the first attempt to integrate textual, visual, and social graph features in one unified framework. |
Jiaqi Zheng; Xi Zhang; Sanchuan Guo; Quan Wang; Wenyu Zang; Yongdong Zhang; |
336 | Table2Graph: Transforming Tabular Data to Unified Weighted Graph Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: While the fixed graph may be sub-optimal to downstream tasks, the sample-wise graph construction is time-consuming during model training and inference. To tackle these issues, we propose a framework named Table2Graph to transform the feature interaction modeling to learning a unified graph. |
Kaixiong Zhou; Zirui Liu; Rui Chen; Li Li; Soo-Hyun Choi; Xia Hu; |
337 | Bridging Differential Privacy and Byzantine-Robustness Via Model Aggregation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we decouple the two issues via robust stochastic model aggregation, in the sense that our proposed DP mechanisms and the defense against Byzantine attacks have separated influence on the learning performance. |
Heng Zhu; Qing Ling; |
338 | Spiking Graph Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose SpikingGCN, an end-to-end framework that aims to integrate the embedding of GCNs with the biofidelity characteristics of SNNs. |
Zulun Zhu; Jiaying Peng; Jintang Li; Liang Chen; Qi Yu; Siqiang Luo; |
339 | Data-Free Adversarial Knowledge Distillation for Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, most of the existing KD methods require a large volume of real data, which are not readily available in practice, and may preclude their applicability in scenarios where the teacher model is trained on rare or hard to acquire datasets. To address this problem, we propose the first end-to-end framework for data-free adversarial knowledge distillation on graph structured data (DFAD-GNN). |
Yuanxin Zhuang; Lingjuan Lyu; Chuan Shi; Carl Yang; Lichao Sun; |
340 | Proximity Enhanced Graph Neural Networks with Channel Contrast Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Inspired by the recent success of contrastive learning approaches, we propose a self-supervised method that aims to learn node representations by maximizing the agreement between representations across generated views and the original graph, without the requirement of any label information. |
Wei Zhuo; Guang Tan; |
341 | On The Utility of Prediction Sets in Human-AI Teams Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, we notice that the predictive sets provided by CP can be very large, which leads to unhelpful AI assistants. To mitigate this, we introduce D-CP, a method to perform CP on some examples and defer to experts. |
Varun Babbar; Umang Bhatt; Adrian Weller; |
342 | Multi-Tier Platform for Cognizing Massive Electroencephalogram Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: An end-to-end platform assembling multiple tiers is built for precisely cognizing brain activities. Being fed massive electroencephalogram (EEG) data, the time-frequency … |
Zheng Chen; Lingwei Zhu; Ziwei Yang; Renyuan Zhang; |
343 | Multi-Level Firing with Spiking DS-ResNet: Enabling Better and Deeper Directly-Trained Spiking Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a multi-level firing (MLF) method based on the existing spatio-temporal back propagation (STBP) method, and spiking dormant-suppressed residual network (spiking DS-ResNet). |
Lang Feng; Qianhui Liu; Huajin Tang; De Ma; Gang Pan; |
344 | Forming Effective Human-AI Teams: Building Machine Learning Models That Complement The Capabilities of Multiple Experts Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose an approach that trains a classification model to complement the capabilities of multiple human experts. |
Patrick Hemmer; Sebastian Schellhammer; Michael Vössing; Johannes Jakubik; Gerhard Satzger; |
345 | Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose a neuron model for releasing burst spikes, a cheap but highly efficient method to solve residual information. |
Yang Li; Yi Zeng; |
346 | Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present Bayesian Team Imitation Learner (BTIL), an imitation learning algorithm to model the behavior of teams performing sequential tasks in Markovian domains. |
Sangwon Seo; Vaibhav V. Unhelkar; |
347 | Signed Neuron with Memory: Towards Simple, Accurate and High-Efficient ANN-SNN Conversion Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we first analyze how the asynchronous spikes in SNNs may cause conversion errors between ANN and SNN. To address this problem, we propose a signed neuron with memory function, which enables almost no accuracy loss during the conversion process, and maintains the properties of asynchronous transmission in the converted SNNs. |
Yuchen Wang; Malu Zhang; Yi Chen; Hong Qu; |
348 | Rethinking InfoNCE: How Many Negative Samples Do You Need? Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we study how many negative samples are optimal for InfoNCE in different scenarios via a semi-quantitative theoretical framework. |
Chuhan Wu; Fangzhao Wu; Yongfeng Huang; |
349 | On Preferences and Priority Rules in Abstract Argumentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Dung’s abstract Argumentation Framework (AF) has emerged as a central formalism for argumentation in AI. Preferences in AF allow to represent the comparative strength of arguments … |
Gianvincenzo Alfano; Sergio Greco; Francesco Parisi; Irina Trubitsyna; |
350 | Beyond Strong-Cyclic: Doing Your Best in Stochastic Environments Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce “best-effort" policies for (not necessarily Markovian) stochastic domains. |
Benjamin Aminof; Giuseppe De Giacomo; Sasha Rubin; Florian Zuleger; |
351 | Annotated Sequent Calculi for Paraconsistent Reasoning and Their Relations to Logical Argumentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce annotated sequent calculi, which are extensions of standard sequent calculi, where sequents are combined with annotations that represent their derivation statuses. |
Ofer Arieli; Kees van Berkel; Christian Straßer; |
352 | Limits and Possibilities of Forgetting in Abstract Argumentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We show the limits and shed light on the possibilities. |
Ringo Baumann; Matti Berthold; |
353 | Body-Decoupled Grounding Via Solving: A Novel Approach on The ASP Bottleneck Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This becomes virulent when grounding of rules, where the variables have to be replaced by constants, leads to a ground pro- gram that is too huge to be processed by the ASP solver. In this work, we tackle this problem by a novel method that decouples non-ground atoms in rules in order to delegate the evaluation of rule bodies to the solving process. |
Viktor Besin; Markus Hecher; Stefan Woltran; |
354 | Verification and Monitoring for First-Order LTL with Persistence-Preserving Quantification Over Finite and Infinite Traces Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we show that in LTL-FOp, which is the fragment of LTL-FO in which quantification is over objects that persist along traces, model checking state-bounded systems becomes decidable over finite and infinite traces. |
Diego Calvanese; Giuseppe De Giacomo; Marco Montali; Fabio Patrizi; |
355 | The Limits of Morality in Strategic Games Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we introduce a notion of limited blameworthiness, with a constraint on the amount of sacrifice required to prevent the outcome. |
Rui Cao; Pavel Naumov; |
356 | On Verifying Expectations and Observations of Intelligent Agents Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Agents have certain expectations, regarding the situation at hand, that are actuated by the relevant protocols, and they eliminate possible worlds in which their expectations do not match with their observations. In this work, we investigate the computational complexity of the model checking problem for POL and prove its PSPACE-completeness. |
Sourav Chakraborty; Avijeet Ghosh; Sujata Ghosh; François Schwarzentruber; |
357 | Personalized Federated Learning With A Graph Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper aims to enhance the knowledge-sharing process in PFL by leveraging the graph-based structural information among clients. |
Fengwen Chen; Guodong Long; Zonghan Wu; Tianyi Zhou; Jing Jiang; |
358 | On The Complexity of Enumerating Prime Implicants from Decision-DNNF Circuits Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We consider the problem Enum·IP of enumerating prime implicants of Boolean functions represented by decision decomposable negation normal form (dec-DNNF) circuits. |
Alexis de Colnet; Pierre Marquis; |
359 | LTLf Synthesis As AND-OR Graph Search: Knowledge Compilation at Work Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we develop a forward-search approach to full-fledged Linear Temporal Logic on finite traces (LTLf) synthesis. |
Giuseppe De Giacomo; Marco Favorito; Jianwen Li; Moshe Y. Vardi; Shengping Xiao; Shufang Zhu; |
360 | Epistemic Logic of Likelihood and Belief Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: As an alternative, qualitative approaches have been introduced to express that one event is no more probable than another. |
James P. Delgrande; Joshua Sack; Gerhard Lakemeyer; Maurice Pagnucco; |
361 | LTL on Weighted Finite Traces: Formal Foundations and Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, its practical usage is still rather limited, as LTLf cannot deal with any quantitative aspect, such as with the costs of realizing some desired behaviour. The paper fills the gap by proposing a weighting framework for LTLf encoding such quantitative aspects in the traces over which it is evaluated. |
Carmine Dodaro; Valeria Fionda; Gianluigi Greco; |
362 | Abstract Argumentation Frameworks with Marginal Probabilities Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We focus on the problems of computing the max and min probabil- ities of extensions over mAAFs under Dung’s se- mantics, characterize their complexity, and provide closed formulas for polynomial cases. |
Bettina Fazzinga; Sergio Flesca; Filippo Furfaro; |
363 | Plausibility Reasoning Via Projected Answer Set Counting – A Hybrid Approach Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a novel hybrid approach for plausibility reasoning under projections, thereby relying on projected answer set counting as basis. |
Johannes K. Fichte; Markus Hecher; Mohamed A. Nadeem; |
364 | Frontiers and Exact Learning of ELI Queries Under DL-Lite Ontologies Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study ELI queries (ELIQs) in the presence of ontologies formulated in the description logic DL-Lite. |
Maurice Funk; Jean Christoph Jung; Carsten Lutz; |
365 | Simulating Sets in Answer Set Programming Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present two new reasoning methods for DLP(S): a semantics-preserving translation of DLP(S) to logic programming with function symbols, which can take advantage of lazy grounding techniques, and a ground-and-solve approach that uses non-monotonic existential rules in the grounding stage. |
Sarah Alice Gaggl; Philipp Hanisch; Markus Krötzsch; |
366 | Linear Temporal Logic Modulo Theories Over Finite Traces Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Despite the general undecidability of these problems, being able to solve satisfiable instances is a compromise worth studying. After motivating and describing such use cases, we provide a sound and complete semi-decision procedure for LTLfMT based on the SMT encoding of a one-pass tree-shaped tableau system. |
Luca Geatti; Alessandro Gianola; Nicola Gigante; |
367 | A Computationally Grounded Logic of ‘Seeing-to-it-that’ Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce a simple model of agency that is based on the concepts of control and attempt. |
Andreas Herzig; Emiliano Lorini; Elise Perrotin; |
368 | Possibilistic Logic Underlies Abstract Dialectical Frameworks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We show that possibilistic logic is the unique logic that can faithfully encode all other semantical concepts for ADFs. Based on this result, we also characterise strong equivalence and introduce possibilistic ADFs. |
Jesse Heyninck; Gabriele Kern-Isberner; Tjitze Rienstra; Kenneth Skiba; Matthias Thimm; |
369 | Lexicographic Entailment, Syntax Splitting and The Drowning Problem Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we show that lexicographic inference satisfies syntax splitting, which means that we can restrict our attention to parts of the belief base that share atoms with a given query, thus seriously restricting the computational costs for many concrete queries. |
Jesse Heyninck; Gabriele Kern-Isberner; Thomas Meyer; |
370 | Computing Concept Referring Expressions for Queries on Horn ALC Ontologies Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Existing approaches, e.g., based on tree automata, can neither be integrated into state-of-the-art OWL reasoners nor are they directly amenable for an efficient implementation. To address this, we devise a novel algorithm that uses highly optimized OWL reasoners as a black box. |
Moritz Illich; Birte Glimm; |
371 | The Egocentric Logic of Preferences Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: The paper studies preferences of agents about other agents in a social network. It proposes a logical system that captures the properties of such preferences, called … |
Junli Jiang; Pavel Naumov; |
372 | In Data We Trust: The Logic of Trust-Based Beliefs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The paper proposes a data-centred approach to reasoning about the interplay between trust and beliefs. |
Junli Jiang; Pavel Naumov; |
373 | Conditional Independence for Iterated Belief Revision Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we define conditional independence as a semantic property of epistemic states and present axioms for iterated belief revision operators to obey conditional independence in general. |
Gabriele Kern-Isberner; Jesse Heyninck; Christoph Beierle; |
374 | Search Space Expansion for Efficient Incremental Inductive Logic Programming from Streamed Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Rerunning an ILP system from scratch each time new examples arrive is inefficient. In this paper we address this problem by presenting IncrementalLAS, a system that uses a new technique, called hypothesis space expansion, to enable a FastLAS-like OPT-sufficient subset to be expanded each time new examples are discovered. |
Mark Law; Krysia Broda; Alessandra Russo; |
375 | Explanations for Negative Query Answers Under Inconsistency-Tolerant Semantics Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we address another important problem, which is explaining why a query is not entailed under an inconsistency-tolerant semantics. |
Thomas Lukasiewicz; Enrico Malizia; Cristian Molinaro; |
376 | Causes of Effects: Learning Individual Responses from Population Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This added information may provide the power to solve central problems, such as explainable AI, legal responsibility, and personalized medicine, all of which demand counterfactual logic. This paper derives, analyzes, and characterizes these new bounds, and illustrates some of their practical applications. |
Scott Mueller; Ang Li; Judea Pearl; |
377 | Inverse Problems for Gradual Semantics Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: A sub-class of such semantics, the so-called weighted semantics, takes, in addition to the graph structure, an initial set of weights over the arguments as input, with these weights affecting the resultant argument ranking. In this work, we consider the inverse problem over such weighted semantics. |
Nir Oren; Bruno Yun; Srdjan Vesic; Murilo Baptista; |
378 | Learning Higher-Order Logic Programs From Failures Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our theoretical framework captures a class of higher-order definitions preserving soundness of existing subsumption-based pruning methods. |
Stanisław J. Purgał; David M. Cerna; Cezary Kaliszyk; |
379 | Revision By Comparison for Ranking Functions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Revision by Comparison (RbC) is a non-prioritized belief revision mechanism on epistemic states that specifies constraints on the plausibility of an input sentence via a designated reference sentence, allowing for kind of relative belief revision. In this paper, we make the strategy underlying RbC more explicit and transfer the mechanism together with its intuitive strengths to a semi-quantitative framework based on ordinal conditional functions where a more elegant implementation of RbC is possible. |
Meliha Sezgin; Gabriele Kern-Isberner; |
380 | Considering Constraint Monotonicity and Foundedness in Answer Set Programming Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This question is challenging and has incurred a debate in answer set programming (ASP). In this paper we address the question by introducing natural logic programs whose expected answer sets and world views violate these properties and thus may be viewed as counter-examples to these requirements. |
Yi-Dong Shen; Thomas Eiter; |
381 | Updating Probability Intervals with Uncertain Inputs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper addresses the problem of updating uncertain information specified in the form of probability intervals with new uncertain inputs also expressed as probability intervals. We place ourselves in the framework of Jeffrey’s rule of conditioning and propose extensions of this conditioning for the interval-based setting. |
Karim Tabia; |
382 | Simple and Effective Relation-based Embedding Propagation for Knowledge Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Although they achieved competitive performance on small KGs, how to efficiently and effectively utilize graph context for large KGs remains an open problem. To this end, we propose the Relation-based Embedding Propagation (REP) method. |
Huijuan Wang; Siming Dai; Weiyue Su; Hui Zhong; Zeyang Fang; Zhengjie Huang; Shikun Feng; Zeyu Chen; Yu Sun; Dianhai Yu; |
383 | Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose to augment the transformer architecture with an external attention mechanism to bring external knowledge and context to bear. |
Yichong Xu; Chenguang Zhu; Shuohang Wang; Siqi Sun; Hao Cheng; Xiaodong Liu; Jianfeng Gao; Pengcheng He; Michael Zeng; Xuedong Huang; |
384 | GL-RG: Global-Local Representation Granularity for Video Captioning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we approach the video captioning task from a new perspective and propose a GL-RG framework for video captioning, namely a Global-Local Representation Granularity. |
Liqi Yan; Qifan Wang; Yiming Cui; Fuli Feng; Xiaojun Quan; Xiangyu Zhang; Dongfang Liu; |
385 | FedDUAP: Federated Learning with Dynamic Update and Adaptive Pruning Using Shared Data on The Server Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel FL framework, i.e., FedDUAP, with two original contributions, to exploit the insensitive data on the server and the decentralized data in edge devices to further improve the training efficiency. |
Hong Zhang; Ji Liu; Juncheng Jia; Yang Zhou; Huaiyu Dai; Dejing Dou; |
386 | Synthesis of Maximally Permissive Strategies for LTLf Specifications Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we study synthesis of maximally permissive strategies for Linear Temporal Logic on finite traces (LTLf) specifications. |
Shufang Zhu; Giuseppe De Giacomo; |
387 | Learning Label Initialization for Time-Dependent Harmonic Extension Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Node classification on graphs can be formulated as the Dirichlet problem on graphs where the signal is given at the labeled nodes, and the harmonic extension is done on the unlabeled nodes. This paper considers a time-dependent version of the Dirichlet problem on graphs and shows how to improve its solution by learning the proper initialization vector on the unlabeled nodes. |
Amitoz Azad; |
388 | Fixed-Budget Best-Arm Identification in Structured Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a general tractable algorithm that incorporates the structure, by successively eliminating suboptimal arms based on their mean reward estimates from a joint generalization model. |
MohammadJavad Azizi; Branislav Kveton; Mohammad Ghavamzadeh; |
389 | One Weird Trick to Improve Your Semi-Weakly Supervised Semantic Segmentation Model Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a method called prediction filtering, which instead of extracting pseudo-labels, just uses the classifier as a classifier: it ignores any segmentation predictions from classes which the classifier is confident are not present. |
Wonho Bae; Junhyug Noh; Milad Jalali Asadabadi; Danica J. Sutherland; |
390 | Logit Mixing Training for More Reliable and Accurate Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Knowing what choice is not the answer and utilizing the relationships between choices, she can improve the prediction accuracy. Inspired by this human reasoning process, we propose a new training strategy to fully utilize inter-class relationships, namely LogitMix. |
Duhyeon Bang; Kyungjune Baek; Jiwoo Kim; Yunho Jeon; Jin-Hwa Kim; Jiwon Kim; Jongwuk Lee; Hyunjung Shim; |
391 | Adversarial Explanations for Knowledge Graph Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a novel black-box approach for performing adversarial attacks against knowledge graph embedding models. |
Patrick Betz; Christian Meilicke; Heiner Stuckenschmidt; |
392 | Not A Number: Identifying Instance Features for Capability-Oriented Evaluation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a new methodology to identify and build informative instance features that can provide explanatory and predictive power to analyse the behaviour of AI systems more robustly. |
Ryan Burnell; John Burden; Danaja Rutar; Konstantinos Voudouris; Lucy Cheke; José Hernández-Orallo; |
393 | Posistive-Unlabeled Learning Via Optimal Transport and Margin Distribution Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Moreover, these methods learn the decision boundary by optimizing the minimum margin, which is not suitable in PU learning due to its sensitivity to label noise. In this paper, we enhance PU learning methods from the above two aspects. |
Nan Cao; Teng Zhang; Xuanhua Shi; Hai Jin; |
394 | Neural Contextual Anomaly Detection for Time Series Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We introduce Neural Contextual Anomaly Detection (NCAD), a framework for anomaly detection on time series that scales seamlessly from the unsupervised to supervised setting, and is applicable to both univariate and multivariate time series. |
Chris U. Carmona; François-Xavier Aubet; Valentin Flunkert; Jan Gasthaus; |
395 | Rethinking The Promotion Brought By Contrastive Learning to Semi-Supervised Node Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we first deeply probe the working mechanism of GCL in SSNC, and find that the promotion brought by GCL is severely unevenly distributed: the improvement mainly comes from subgraphs with less annotated information, which is fundamentally different from contrastive learning in other fields. |
Deli Chen; Yankai Lin; Lei Li; Xuancheng Ren; Peng Li; Jie Zhou; Xu Sun; |
396 | Self-Supervised Mutual Learning for Dynamic Scene Reconstruction of Spiking Camera Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a novel pretext task to build a self-supervised reconstruction framework for spiking cameras. |
Shiyan Chen; Chaoteng Duan; Zhaofei Yu; Ruiqin Xiong; Tiejun Huang; |
397 | DDDM: A Brain-Inspired Framework for Robust Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Drawing inspiration from the DDM, we propose the Dropout-based Drift-Diffusion Model (DDDM) that combines test-phase dropout and the DDM for improving the robustness for arbitrary neural networks. |
Xiyuan Chen; Xingyu Li; Yi Zhou; Tianming Yang; |
398 | Better Embedding and More Shots for Few-shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Suppose we propose to extract embedding from the embedding network. |
Ziqiu Chi; Zhe Wang; Mengping Yang; Wei Guo; Xinlei Xu; |
399 | Heterogeneous Ensemble Knowledge Transfer for Training Large Models in Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a novel ensemble knowledge transfer method named Fed-ET in which small models (different in architecture) are trained on clients, and used to train a larger model at the server. |
Yae Jee Cho; Andre Manoel; Gauri Joshi; Robert Sim; Dimitrios Dimitriadis; |
400 | Can We Find Neurons That Cause Unrealistic Images in Deep Generative Networks? Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this study, by analyzing the statistics and the roles for those neurons, we empirically show that rarely activated neurons are related to the failure results of making diverse objects and inducing artifacts. |
Hwanil Choi; Wonjoon Chang; Jaesik Choi; |
401 | Geometric Transformer for End-to-End Molecule Properties Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we introduce a Transformer-based architecture for molecule property prediction, which is able to capture the geometry of the molecule. |
Yoni Choukroun; Lior Wolf; |
402 | Multiband VAE: Latent Space Alignment for Knowledge Consolidation in Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose a new method for unsupervised generative continual learning through realignment of Variational Autoencoder’s latent space. |
Kamil Deja; Paweł Wawrzyński; Wojciech Masarczyk; Daniel Marczak; Tomasz Trzciński; |
403 | Reinforcement Learning with Option Machines Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce a framework for increasing sample efficiency of RL algorithms. |
Floris den Hengst; Vincent Francois-Lavet; Mark Hoogendoorn; Frank van Harmelen; |
404 | Coherent Probabilistic Aggregate Queries on Long-horizon Forecasts Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we present a novel probabilistic forecasting method that produces forecasts that are coherent in terms of base level and predicted aggregate statistics. |
Prathamesh Deshpande; Sunita Sarawagi; |
405 | Taylor-Lagrange Neural Ordinary Differential Equations: Toward Fast Training and Evaluation of Neural ODEs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: By contrast, we accelerate the evaluation and the training of NODEs by proposing a data-driven approach to their numerical integration. |
Franck Djeumou; Cyrus Neary; Eric Goubault; Sylvie Putot; Ufuk Topcu; |
406 | Residual Contrastive Learning for Image Reconstruction: Learning Transferable Representations from Noisy Images Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a new label-efficient learning paradigm based on residuals, residual contrastive learning (RCL), and derive an unsupervised visual representation learning framework, suitable for low-level vision tasks with noisy inputs. |
Nanqing Dong; Matteo Maggioni; Yongxin Yang; Eduardo Pérez-Pellitero; Ales Leonardis; Steven McDonagh; |
407 | Function-words Adaptively Enhanced Attention Networks for Few-Shot Inverse Relation Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a function words adaptively enhanced attention framework (FAEA) for few-shot inverse relation classification, in which a hybrid attention model is designed to attend class-related function words based on meta-learning. |
Chunliu Dou; Shaojuan Wu; Xiaowang Zhang; Zhiyong Feng; Kewen Wang; |
408 | Multi-Vector Embedding on Networks with Taxonomies Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose HIerarchical Multi-vector Embedding (HIME), which solves the underfitting problem by adaptively learning multiple ‘branch vectors’ for each node to dynamically fit separate sets of labels in a hierarchy-aware embedding space. |
Yue Fan; Xiuli Ma; |
409 | Fixed-Budget Pure Exploration in Multinomial Logit Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we investigate pure exploration problem in Multinomial Logit bandit(MNL-bandit) under fixed budget settings, a problem motivated by real-time applications in online advertising and retailing. |
Boli Fang; |
410 | Learning Unforgotten Domain-Invariant Representations for Online Unsupervised Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we discuss Online UDA (OUDA) which assumes that the target samples are arriving sequentially as a small batch. |
Cheng Feng; Chaoliang Zhong; Jie Wang; Ying Zhang; Jun Sun; Yasuto Yokota; |
411 | Comparison Knowledge Translation for Generalizable Image Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we attempt to build a generalizable framework that emulates the humans’ recognition mechanism in the image classification task, hoping to improve the classification performance on unseen categories with the support of annotations of other categories. |
Zunlei Feng; Tian Qiu; Sai Wu; Xiaotuan Jin; Zengliang He; Mingli Song; Huiqiong Wang; |
412 | Non-Cheating Teaching Revisited: A New Probabilistic Machine Teaching Model Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We show a simple procedure that builds the witness joint distribution from the ground joint distribution. |
Cèsar Ferri; José Hernández-Orallo; Jan Arne Telle; |
413 | DeepExtrema: A Deep Learning Approach for Forecasting Block Maxima in Time Series Data Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper presents DeepExtrema, a novel framework that combines a deep neural network (DNN) with generalized extreme value (GEV) distribution to forecast the block maximum value of a time series. |
Asadullah Hill Galib; Andrew McDonald; Tyler Wilson; Lifeng Luo; Pang-Ning Tan; |
414 | Multi-view Unsupervised Graph Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we design a new multi-view unsupervised graph representation learning method including adaptive data augmentation and multi-view contrastive learning, to address some issues of contrastive learning ignoring the information from feature space. |
Jiangzhang Gan; Rongyao Hu; Mengmeng Zhan; Yujie Mo; Yingying Wan; Xiaofeng Zhu; |
415 | A Reinforcement Learning-Informed Pattern Mining Framework for Multivariate Time Series Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a reinforcement learning (RL) informed PAttern Mining framework (RLPAM) to identify interpretable yet important patterns for MTS classification. |
Ge Gao; Qitong Gao; Xi Yang; Miroslav Pajic; Min Chi; |
416 | Bootstrapping Informative Graph Augmentation Via A Meta Learning Approach Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We then clarify that a "good" graph augmentation must have uniformity at the instance-level and informativeness at the feature-level. To this end, we propose a novel approach to learning a graph augmenter that can generate an augmentation with uniformity and informativeness. |
Hang Gao; Jiangmeng Li; Wenwen Qiang; Lingyu Si; Fuchun Sun; Changwen Zheng; |
417 | Learning First-Order Rules with Differentiable Logic Program Semantics Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce a novel differentiable inductive logic programming (ILP) model, called differentiable first-order rule learner (DFOL), which finds the correct LPs from relational facts by searching for the interpretable matrix representations of LPs. |
Kun Gao; Katsumi Inoue; Yongzhi Cao; Hanpin Wang; |
418 | Attributed Graph Clustering with Dual Redundancy Reduction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Specifically, for the input space redundancy reduction, we introduce an adversarial learning mechanism to adaptively learn a redundant edge-dropping matrix to ensure the diversity of the compared sample pairs. |
Lei Gong; Sihang Zhou; Wenxuan Tu; Xinwang Liu; |
419 | Sample Complexity Bounds for Robustly Learning Decision Lists Against Evasion Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: A fundamental problem in adversarial machine learning is to quantify how much training data is needed in the presence of evasion attacks. In this paper we address this issue within the framework of PAC learning, focusing on the class of decision lists. |
Pascale Gourdeau; Varun Kanade; Marta Kwiatkowska; James Worrell; |
420 | RoboGNN: Robustifying Node Classification Under Link Perturbation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper introduces RoboGNN, a novel framework that simultaneously robustifies an input classifier to a counterpart with certifiable robustness, and suggests desired graph representation with auxiliary links to ensure the robustness guarantee. |
Sheng Guan; Hanchao Ma; Yinghui Wu; |
421 | Option Transfer and SMDP Abstraction with Successor Features Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we study joint temporal and state abstraction in reinforcement learning, where temporally-extended actions in the form of options induce temporal abstractions, while aggregation of similar states with respect to abstract options induces state abstractions. |
Dongge Han; Sebastian Tschiatschek; |
422 | To Trust or Not To Trust Prediction Scores for Membership Inference Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Membership inference attacks (MIAs) aim to determine whether a specific sample was used to train a predictive model. |
Dominik Hintersdorf; Lukas Struppek; Kristian Kersting; |
423 | Leveraging Class Abstraction for Commonsense Reinforcement Learning Via Residual Policy Gradient Methods Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose to use the subclass relationships present in open-source knowledge graphs to abstract away from specific objects. |
Niklas Hopner; Ilaria Tiddi; Herke van Hoof; |
424 | Learning Continuous Graph Structure with Bilevel Programming for Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: It is challenging due to the non-differentiable discrete graph structure and lack of ground-truth. In this paper, we address these problems and propose a novel graph structure learning framework for GNNs. |
Minyang Hu; Hong Chang; Bingpeng Ma; Shiguang Shan; |
425 | SHAPE: An Unified Approach to Evaluate The Contribution and Cooperation of Individual Modalities Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose the SHapley vAlue-based PErceptual (SHAPE) scores that measure the marginal contribution of individual modalities and the degree of cooperation across modalities. |
Pengbo Hu; Xingyu Li; Yi Zhou; |
426 | Enhancing Unsupervised Domain Adaptation Via Semantic Similarity Constraint for Medical Image Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This work proposes a novel unsupervised cross-modality adaptive segmentation method for medical images to tackle the performance degradation caused by the severe domain shift when neural networks are being deployed to unseen modalities. |
Tao Hu; Shiliang Sun; Jing Zhao; Dongyu Shi; |
427 | Type-aware Embeddings for Multi-Hop Reasoning Over Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To leverage type information, we propose a novel type-aware model, TypE-aware Message Passing (TEMP), which enhances the entity and relation representation in queries, and simultaneously improves generalization, and deductive and inductive reasoning. |
Zhiwei Hu; Victor Gutierrez Basulto; Zhiliang Xiang; Xiaoli Li; Ru Li; Jeff Z. Pan; |
428 | Reconstructing Diffusion Networks from Incomplete Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we study topology reconstruction of a diffusion network with incomplete observations of the node infection statuses. |
Hao Huang; Keqi Han; Beicheng Xu; Ting Gan; |
429 | FLS: A New Local Search Algorithm for K-means with Smaller Search Space Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a fast and practical local search algorithm for the k-means problem. |
Junyu Huang; Qilong Feng; Ziyun Huang; Jinhui Xu; Jianxin Wang; |
430 | Robust Reinforcement Learning As A Stackelberg Game Via Adaptively-Regularized Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we introduce a novel hierarchical formulation of robust RL — a general-sum Stackelberg game model called RRL-Stack — to formalize the sequential nature and provide extra flexibility for robust training. |
Peide Huang; Mengdi Xu; Fei Fang; Ding Zhao; |
431 | On The Channel Pruning Using Graph Convolution Network for Convolutional Neural Network Acceleration Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Inspired by two popular pruning criteria, i.e. magnitude and similarity, this paper proposes a novel structural pruning method based on Graph Convolution Network (GCN) to further promote compression performance. |
Di Jiang; Yuan Cao; Qiang Yang; |
432 | Graph Masked Autoencoder Enhanced Predictor for Neural Architecture Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a graph masked autoencoder (GMAE) enhanced predictor, which can reduce the dependence on supervision data by self-supervised pre-training with untrained architectures. |
Kun Jing; Jungang Xu; Pengfei Li; |
433 | Online Evasion Attacks on Recurrent Models:The Power of Hallucinating The Future Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a general attack framework for online tasks incorporating the unique constraints of the online setting different from offline tasks. |
Byunggill Joe; Insik Shin; Jihun Hamm; |
434 | Set Interdependence Transformer: Set-to-Sequence Neural Networks for Permutation Learning and Structure Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our aim is to enhance their ability to efficiently model higher-order interactions through an additional interdependence component. |
Mateusz Jurewicz; Leon Derczynski; |
435 | Relational Abstractions for Generalized Reinforcement Learning on Symbolic Problems Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Reinforcement learning in problems with symbolic state spaces is challenging due to the need for reasoning over long horizons. This paper presents a new approach that utilizes relational abstractions in conjunction with deep learning to learn a generalizable Q-function for such problems. |
Rushang Karia; Siddharth Srivastava; |
436 | Data Augmentation for Learning to Play in Text-Based Games Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose Transition-Matching Permutation, a novel data augmentation technique for text-based games, where we identify phrase permutations that match as many transitions in the trajectory data. |
Jinhyeon Kim; Kee-Eung Kim; |
437 | Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We design a Self-Predictive Dynamics (SPD) method to extract task-relevant features efficiently, even in unseen observations after training. |
Kyungsoo Kim; Jeongsoo Ha; Yusung Kim; |
438 | DyGRAIN: An Incremental Learning Framework for Dynamic Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we raise a crucial challenge of incremental learning for dynamic graphs as time-varying receptive fields, and propose a novel incremental learning framework, DyGRAIN, to mitigate time-varying receptive fields and catastrophic forgetting. |
Seoyoon Kim; Seongjun Yun; Jaewoo Kang; |
439 | Thompson Sampling for Bandit Learning in Matching Markets Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we provide the first regret analysis for TS in the new setting of iterative matching markets. |
Fang Kong; Junming Yin; Shuai Li; |
440 | Multi-policy Grounding and Ensemble Policy Learning for Transfer Learning with Dynamics Mismatch Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a new transfer learning algorithm between tasks with different dynamics. |
Hyun-Rok Lee; Ram Ananth Sreenivasan; Yeonjeong Jeong; Jongseong Jang; Dongsub Shim; Chi-Guhn Lee; |
441 | Pseudo-spherical Knowledge Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose an alternative distillation objective by maximizing the scoring rule, which quantitatively measures the agreement of a distribution to the reference distribution. |
Kyungmin Lee; Hyeongkeun Lee; |
442 | Libra-CAM: An Activation-Based Attribution Based on The Linear Approximation of Deep Neural Nets and Threshold Calibration Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose Libra-CAM, a new CAM-style attribution method based on the best linear approximation of the layer (as a function) between the penultimate activation and the target-class score output. |
Sangkyun Lee; Sungmin Han; |
443 | SGAT: Simplicial Graph Attention Network Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, there can be nonlinear, high-order interactions involving multiple nodes or edges. In this paper, we present Simplicial Graph Attention Network (SGAT), a simplicial complex approach to represent such high-order interactions by placing features from non-target nodes on the simplices. |
See Hian Lee; Feng Ji; Wee Peng Tay; |
444 | Learning General Gaussian Mixture Model with Integral Cosine Similarity Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper presents a new learning method called G$^2$M$^2$ (General Gaussian Mixture Model) by fitting an unnormalized Gaussian mixture function (UGMF) to a data distribution. |
Guanglin Li; Bin Li; Changsheng Chen; Shunquan Tan; Guoping Qiu; |
445 | Ridgeless Regression with Random Features Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we investigate the statistical properties of ridgeless regression with random features and stochastic gradient descent. |
Jian Li; Yong Liu; Yingying Zhang; |
446 | Learning from Students: Online Contrastive Distillation Network for General Continual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, it accumulates the inherent old model’s response bias and is not robust to model changes. To this end, we propose an Online Contrastive Distillation Network (OCD-Net) to tackle these problems, which explores the merit of the student model in each time step to guide the training process of the student model. |
Jin Li; Zhong Ji; Gang Wang; Qiang Wang; Feng Gao; |
447 | Cross-modal Representation Learning and Relation Reasoning for Bidirectional Adaptive Manipulation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce a robust solution for CAM, which includes two essential modules, namely Heterogeneous Representation Learning (HRL) and Cross-modal Relation Reasoning (CRR). |
Lei Li; Kai Fan; Chun Yuan; |
448 | Neural PCA for Flow-Based Representation Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose Neural Principal Component Analysis (Neural-PCA) that operates in full dimensionality while capturing principal components in descending order. |
Shen Li; Bryan Hooi; |
449 | Pruning-as-Search: Efficient Neural Architecture Search Via Channel Pruning and Structural Reparameterization Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we revisit the problem of layer-width optimization and propose Pruning-as-Search (PaS), an end-to-end channel pruning method to search out desired sub-network automatically and efficiently. |
Yanyu Li; Pu Zhao; Geng Yuan; Xue Lin; Yanzhi Wang; Xin Chen; |
450 | Rethinking The Setting of Semi-supervised Learning on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we highlight the significant influence of tuning hyper-parameters, which leverages the label information in the validation set to improve the performance. |
Ziang Li; Ming Ding; Weikai Li; Zihan Wang; Ziyu Zeng; Yukuo Cen; Jie Tang; |
451 | Contrastive Multi-view Hyperbolic Hierarchical Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This raises a less investigated problem, i.e., multi-view hierarchical clustering, to better understand the hierarchical structure of multi-view data. To this end, we propose a novel neural network-based model, namely Contrastive Multi-view Hyperbolic Hierarchical Clustering(CMHHC). |
Fangfei Lin; Bing Bai; Kun Bai; Yazhou Ren; Peng Zhao; Zenglin Xu; |
452 | JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Learning rational behaviors in open-world games like Minecraft remains to be challenging for Reinforcement Learning (RL) research due to the compound challenge of partial observability, high-dimensional visual perception and delayed reward. To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration. |
Zichuan Lin; Junyou Li; Jianing Shi; Deheng Ye; Qiang Fu; Wei Yang; |
453 | Declaration-based Prompt Tuning for Visual Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To alleviate the problem, we propose an innovative VL fine-tuning paradigm (named Declaration-based Prompt Tuning, abbreviated as DPT), which fine-tunes the model for downstream VQA using the pre-training objectives, boosting the effective adaptation of pre-trained models to the downstream task. |
Yuhang Liu; Wei Wei; Daowan Peng; Feida Zhu; |
454 | Projected Gradient Descent Algorithms for Solving Nonlinear Inverse Problems with Generative Priors Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose projected gradient descent (PGD) algorithms for signal estimation from noisy nonlinear measurements. |
Zhaoqiang Liu; Jun Han; |
455 | SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Deep neural networks are prone to overfitting noisy labels, resulting in poor generalization performance. To overcome this problem, we present a simple and effective method self-ensemble label correction (SELC) to progressively correct noisy labels and refine the model. |
Yangdi Lu; Wenbo He; |
456 | Exploring Binary Classification Hidden Within Partial Label Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: On which basis, current researches either directly model P(x | y) under different data generation assumptions or propose various surrogate multiclass losses, which all aim to encourage the model-based Pθ(y ∈ s | x)→1 implicitly. In this work, instead, we explicitly construct a binary classification task toward P(y ∈ s | x) based on the discriminative model, that is to predict whether the model-output label of x is one of its candidate labels. |
Hengheng Luo; Yabin Zhang; Suyun Zhao; Hong Chen; Cuiping Li; |
457 | Teaching LTLf Satisfiability Checking to Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: It is a challenge to characterize the syntactic and semantic features of LTLf via neural networks. To tackle this challenge, we propose LTLfNet, a recursive neural network that captures syntactic features of LTLf by recursively combining the embeddings of sub-formulae. |
Weilin Luo; Hai Wan; Jianfeng Du; Xiaoda Li; Yuze Fu; Rongzhen Ye; Delong Zhang; |
458 | Towards Robust Unsupervised Disentanglement of Sequential Data — A Case Study Using Music Audio Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we show that the vanilla DSAE suffers from being sensitive to the choice of model architecture and capacity of the dynamic latent variables, and is prone to collapse the static latent variable. |
Yin-Jyun Luo; Sebastian Ewert; Simon Dixon; |
459 | Deep Graph Matching for Partial Label Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we formulate the task of PLL problem as an “instance-label” matching selection problem, and propose a DeepGNN-based graph matching PLL approach to solve it. |
Gengyu Lyu; Yanan Wu; Songhe Feng; |
460 | Locally Normalized Soft Contrastive Clustering for Compact Clusters Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, as many recent datasets are enormous and noisy, getting a clear boundary between different clusters is challenging with existing methods that mainly focus on contracting similar samples together and overlooking samples near boundary of clusters in the latent space. In this regard, we propose an end-to-end deep clustering algorithm, i.e., Locally Normalized Soft Contrastive Clustering (LNSCC). |
Xin Ma; Won Hwa Kim; |
461 | Game Redesign in No-regret Game Playing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present game redesign algorithms with the guarantee that the target action profile is played in T-o(T) rounds while incurring only o(T) cumulative design cost. |
Yuzhe Ma; Young Wu; Xiaojin Zhu; |
462 | COMET Flows: Towards Generative Modeling of Multivariate Extremes and Tail Dependence Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In particular, existing normalizing flow architectures struggle to model multivariate extremes, characterized by heavy-tailed marginal distributions and asymmetric tail dependence among variables. In light of this shortcoming, we propose COMET (COpula Multivariate ExTreme) Flows, which decompose the process of modeling a joint distribution into two parts: (i) modeling its marginal distributions, and (ii) modeling its copula distribution. |
Andrew McDonald; Pang-Ning Tan; Lifeng Luo; |
463 | Tessellation-Filtering ReLU Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We identify tessellation-filtering ReLU neural networks that, when composed with another ReLU network, keep its non-redundant tessellation unchanged or reduce it.The additional network complexity modifies the shape of the decision surface without increasing the number of linear regions. |
Bernhard A. Moser; Michal Lewandowski; Somayeh Kargaran; Werner Zellinger; Battista Biggio; Christoph Koutschan; |
464 | A Few Seconds Can Change Everything: Fast Decision-based Attacks Against DNNs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To bridge the gap and enlarge real threats to commercial applications, we propose a novel and efficient decision-based attack against black-box models, dubbed FastDrop, which only requires a few queries and work well under strong defenses. |
Ningping Mou; Baolin Zheng; Qian Wang; Yunjie Ge; Binqing Guo; |
465 | Escaping Feature Twist: A Variational Graph Auto-Encoder for Node Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Moreover, we find that this inappropriate flattening leads to clustering deterioration by twisting the curved structures. To address this problem, which we call Feature Twist, we propose a variational graph auto-encoder that can smooth the local curves before gradually flattening the global structures. |
Nairouz Mrabah; Mohamed Bouguessa; Riadh Ksantini; |
466 | Composing Neural Learning and Symbolic Reasoning with An Application to Visual Discrimination Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose a compositional neurosymbolic framework that combines a neural network to detect objects and relationships with a symbolic learner that finds interpretable discriminators. |
Adithya Murali; Atharva Sehgal; Paul Krogmeier; P. Madhusudan; |
467 | Certified Robustness Via Randomized Smoothing Over Multiplicative Parameters of Input Transformations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a novel approach to randomized smoothing over multiplicative parameters. |
Nikita Muravev; Aleksandr Petiushko; |
468 | Weakly-supervised Text Classification with Wasserstein Barycenters Regularization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: These weak supervisions are much more cheaper and easy to collect in real-world scenarios. To resolve this task, we propose a novel deep classification model, namely Weakly-supervised Text Classification with Wasserstein Barycenter Regularization (WTC-WBR). |
Jihong Ouyang; Yiming Wang; Ximing Li; Changchun Li; |
469 | Search-based Reinforcement Learning Through Bandit Linear Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The development of AlphaZero was a breakthrough in search-based reinforcement learning, by employing a given world model in a Monte-Carlo tree search (MCTS) algorithm to incrementally learn both an action policy and a value estimation. |
Milan Peelman; Antoon Bronselaer; Guy De Tré; |
470 | On The Optimization of Margin Distribution Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Recent years have witnessed the increasing empirical studies on the optimization of margin distribution according to different statistics such as medium margin, average margin, margin variance, etc., whereas there is a relative paucity of theoretical understanding. In this work, we take one step on this direction by providing a new generalization error bound, which is heavily relevant to margin distribution by incorporating ingredients such as average margin and semi-variance, a new margin statistics for the characterization of margin distribution. |
Meng-Zhang Qian; Zheng Ai; Teng Zhang; Wei Gao; |
471 | Understanding The Limits of Poisoning Attacks in Episodic Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate any order-optimal learning algorithm towards a targeted policy in episodic RL and examines the potential damage of two natural types of poisoning attacks, i.e., the manipulation of reward or action. |
Anshuka Rangi; Haifeng Xu; Long Tran-Thanh; Massimo Franceschetti; |
472 | Multi-Armed Bandit Problem with Temporally-Partitioned Rewards: When Partial Feedback Counts Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We provide two algorithms to address TP-MAB problems, namely, TP-UCB-FR and TP-UCB-EW, which exploit the partial information disclosed by the reward collected over time. |
Giulia Romano; Andrea Agostini; Francesco Trovò; Nicola Gatti; Marcello Restelli; |
473 | Markov Abstractions for PAC Reinforcement Learning in Non-Markov Decision Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Our work aims at developing reinforcement learning algorithms that do not rely on the Markov assumption. |
Alessandro Ronca; Gabriel Paludo Licks; Giuseppe De Giacomo; |
474 | PAnDR: Fast Adaptation to New Environments from Offline Experiences Via Decoupling Policy and Environment Representations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose Policy Adaptation with Decoupled Representations (PAnDR) for fast policy adaptation. |
Tong Sang; Hongyao Tang; Yi Ma; Jianye Hao; Yan Zheng; Zhaopeng Meng; Boyan Li; Zhen Wang; |
475 | Federated Multi-Task Attention for Cross-Individual Human Activity Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, this assumption is impractical in real-world scenarios where the same activity is frequently performed differently by different individuals. To tackle this issue, we propose FedMAT, a Federated Multi-task ATtention framework for HAR, which extracts and fuses shared as well as individual-specific multi-modal sensor data features. |
Qiang Shen; Haotian Feng; Rui Song; Stefano Teso; Fausto Giunchiglia; Hao Xu; |
476 | Lexicographic Multi-Objective Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work we introduce reinforcement learning techniques for solving lexicographic multi-objective problems. |
Joar Skalse; Lewis Hammond; Charlie Griffin; Alessandro Abate; |
477 | Dynamic Sparse Training for Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we introduce for the first time a dynamic sparse training approach for deep reinforcement learning to accelerate the training process. |
Ghada Sokar; Elena Mocanu; Decebal Constantin Mocanu; Mykola Pechenizkiy; Peter Stone; |
478 | CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Nevertheless, we empirically find that not all samples are equally important and hence simply injecting more augmented inputs may instead cause instability in Q-learning. In this paper, we approach this problem systematically by developing a model-agnostic Contrastive-Curiosity-driven Learning Framework (CCLF), which can fully exploit sample importance and improve learning efficiency in a self-supervised manner. |
Chenyu Sun; Hangwei Qian; Chunyan Miao; |
479 | Memory Augmented State Space Model for Time Series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Conventional SSM with fixed-order Markovian assumption often falls short in handling the long-range temporal dependencies and/or highly non-linear correlation in time-series data, which is crucial for accurate forecasting. To this extend, we present External Memory Augmented State Space Model (EMSSM) within the sequential Monte Carlo (SMC) framework. |
Yinbo Sun; Lintao Ma; Yu Liu; Shijun Wang; James Zhang; YangFei Zheng; Hu Yun; Lei Lei; Yulin Kang; Llinbao Ye; |
480 | MMT: Multi-way Multi-modal Transformer for Multimodal Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: The heart of multimodal learning research lies the challenge of effectively exploiting fusion representations among multiple modalities.However, existing two-way cross-modality … |
Jiajia Tang; Kang Li; Ming Hou; Xuanyu Jin; Wanzeng Kong; Yu Ding; Qibin Zhao; |
481 | RecipeRec: A Heterogeneous Graph Learning Model for Recipe Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we formalize the problem of recipe recommendation with graphs to incorporate the collaborative signal into recipe recommendation through graph modeling. |
Yijun Tian; Chuxu Zhang; Zhichun Guo; Chao Huang; Ronald Metoyer; Nitesh V. Chawla; |
482 | Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we formalize the problem of multi-modal recipe representation learning to integrate the visual, textual, and relational information into recipe embeddings. |
Yijun Tian; Chuxu Zhang; Zhichun Guo; Yihong Ma; Ronald Metoyer; Nitesh V. Chawla; |
483 | Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper proposes a novel neural-network-based approach to progressively and autonomously develop pixel-wise representations in a video stream. |
Matteo Tiezzi; Simone Marullo; Lapo Faggi; Enrico Meloni; Alessandro Betti; Stefano Melacci; |
484 | Approximate Exploitability: Learning A Best Response Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce ISMCTS-BR, a scalable search-based deep reinforcement learning algorithm for learning a best response to an agent, approximating worst-case performance. |
Finbarr Timbers; Nolan Bard; Edward Lockhart; Marc Lanctot; Martin Schmid; Neil Burch; Julian Schrittwieser; Thomas Hubert; Michael Bowling; |
485 | Initializing Then Refining: A Simple Graph Attribute Imputation Network Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Representation learning on the attribute-missing graphs, whose connection information is complete while the attribute information of some nodes is missing, is an important yet … |
Wenxuan Tu; Sihang Zhou; Xinwang Liu; Yue Liu; Zhiping Cai; En Zhu; Changwang Zhang; Jieren Cheng; |
486 | Bounded Memory Adversarial Bandits with Composite Anonymous Delayed Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study the adversarial bandit problem with composite anonymous delayed feedback. |
Zongqi Wan; Xiaoming Sun; Jialin Zhang; |
487 | Unsupervised Misaligned Infrared and Visible Image Fusion Via Cross-Modality Image Generation and Registration Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To overcome the obstacles, in this paper, we present a robust cross-modality generation-registration paradigm for unsupervised misaligned infrared and visible image fusion (IVIF). |
Di Wang; Jinyuan Liu; Xin Fan; Risheng Liu; |
488 | Multi-Task Personalized Learning with Sparse Network Lasso Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Personalized learning is recently proposed to learn sample-specific local models by utilizing sample heterogeneity, however, directly applying it in the multi-task learning setting poses three key challenges: 1) model sample homogeneity, 2) prevent from over-parameterization and 3) capture task correlations. In this paper, we propose a novel multi-task personalized learning method to handle these challenges. |
Jiankun Wang; Lu Sun; |
489 | IMO^3: Interactive Multi-Objective Off-Policy Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: As an alternative, we propose Interactive Multi-Objective Off-policy Optimization (IMO^3). |
Nan Wang; Hongning Wang; Maryam Karimzadehgan; Branislav Kveton; Craig Boutilier; |
490 | Modeling Spatio-temporal Neighbourhood for Personalized Point-of-interest Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Specifically, in STGCAN, we construct receptive fields on TKG to aggregate neighbourhoods of user and location respectively at each timestamp. |
Xiaolin Wang; Guohao Sun; Xiu Fang; Jian Yang; Shoujin Wang; |
491 | Multi-Player Multi-Armed Bandits with Finite Shareable Resources Arms: Learning Algorithms & Applications Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose an MMAB with shareable resources as an extension of the collision and non-collision settings. |
Xuchuang Wang; Hong Xie; John C. S. Lui; |
492 | Estimation and Comparison of Linear Regions for ReLU Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: More specifically, we provide both theoretical and empirical evidence for the point of view that shallow networks tend to have higher complexity than deep ones when the total number of neurons is fixed. In the theoretical part, we prove that this is the case for networks whose neurons in the hidden layers are arranged in the forms of 1x2n, 2xn and nx2; in the empirical part, we implement an algorithm that precisely tracks (hence counts) all the linear regions, and run it on networks with various structures. |
Yuan Wang; |
493 | Self-paced Supervision for Multi-source Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Thus the domain shifts between certain of domains and target domain are not effectively relieved, resulting in that these domains are not fully exploited and even may have a negative influence on multi-source domain adaptation task. To address such challenge, we propose a multi-source domain adaptation method to gradually improve the adaptation ability of each source domain by producing more high-confident pseudo-labels with self-paced learning for conditional distribution alignment. |
Zengmao Wang; Chaoyang Zhou; Bo Du; Fengxiang He; |
494 | Value Refinement Network (VRN) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In robotic tasks, we encounter the unique strengths of (1) reinforcement learning (RL) that can handle high-dimensional observations as well as unknown, complex dynamics and (2) planning that can handle sparse and delayed rewards given a dynamics model. Combining these strengths of RL and planning, we propose the Value Refinement Network (VRN), in this work. |
Jan Wöhlke; Felix Schmitt; Herke van Hoof; |
495 | EMGC²F: Efficient Multi-view Graph Clustering with Comprehensive Fusion Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes an Efficient Multi-view Graph Clustering with Comprehensive Fusion (EMGC²F) model and a corresponding efficient optimization algorithm to address multi-view graph clustering tasks effectively and efficiently. |
Danyang Wu; Jitao Lu; Feiping Nie; Rong Wang; Yuan Yuan; |
496 | A Unified Meta-Learning Framework for Dynamic Transfer Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, most existing works assume both tasks are sampled from a stationary task distribution, thereby leading to the sub-optimal performance for dynamic tasks drawn from a non-stationary task distribution in real scenarios. To bridge this gap, in this paper, we study a more realistic and challenging transfer learning setting with dynamic tasks, i.e., source and target tasks are continuously evolving over time. |
Jun Wu; Jingrui He; |
497 | A Simple Yet Effective Method for Graph Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Here, we investigate the feasibility of improving graph classification performance while simplifying the learning process. |
Junran Wu; Shangzhe Li; Jianhao Li; Yicheng Pan; Ke Xu; |
498 | Stabilizing and Enhancing Link Prediction Through Deepened Graph Auto-Encoders Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we overcome the limitation of current methods for link prediction of non-Euclidean network data, which can only use shallow GAEs and variational GAEs. |
Xinxing wu; Qiang Cheng; |
499 | Automatically Gating Multi-Frequency Patterns Through Rectified Continuous Bernoulli Units with Theoretical Principles Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, our contributions are three-fold: 1) we propose a general Rectified Continuous Bernoulli (ReCB) unit paired with an efficient variational Bayesian learning paradigm, to automatically detect/gate/represent different frequency responses; 2) our numerically-tight theoretical framework proves that ReCB-based networks can achieve the optimal representation ability, which is O(m^{η/(d^2)}) times better than that of popular neural networks, for a hidden dimension of m, an input dimension of d, and a Lipschitz constant of η; 3) we provide comprehensive empirical evidence showing that ReCB-based networks can keenly learn multi-frequency patterns and push the state-of-the-art performance. |
Zheng-Fan Wu; Yi-Nan Feng; Hui Xue; |
500 | Information Augmentation for Few-shot Node Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address in issues, this paper proposes a new data augmentation method to conduct FSNC on the graph data including parameter initialization and parameter fine-tuning. |
Zongqian Wu; Peng Zhou; Guoqiu Wen; Yingying Wan; Junbo Ma; Debo Cheng; Xiaofeng Zhu; |
501 | Adversarial Bi-Regressor Network for Domain Adaptive Regression Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a novel method Adversarial Bi-Regressor Network (ABRNet) to seek more effective cross- domain regression model. |
Haifeng Xia; Pu Wang; Toshiaki Koike-Akino; Ye Wang; Philip Orlik; Zhengming Ding; |
502 | Ambiguity-Induced Contrastive Learning for Instance-Dependent Partial Label Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: While a more practical setting in the wild should be instance-dependent, namely, the CLs depend on both the true label and the instance itself, such that each CL may describe the instance from some sensory channel, thereby providing some noisy but really valid information about the instance. In this paper, we leverage such additional information acquired from the ambiguity and propose AmBiguity-induced contrastive LEarning (ABLE) under the framework of contrastive learning. |
Shi-Yu Xia; Jiaqi Lv; Ning Xu; Xin Geng; |
503 | Neuro-Symbolic Verification of Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: While adversarial robustness and fairness fall under this category, many real-world properties (e.g., "an autonomous vehicle has to stop in front of a stop sign") remain outside the scope of existing verification technology. To mitigate this severe practical restriction, we introduce a novel framework for verifying neural networks, named neuro-symbolic verification. |
Xuan Xie; Kristian Kersting; Daniel Neider; |
504 | MultiQuant: Training Once for Multi-bit Quantization of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This work proposes a multi-bit quantization framework (MultiQuant) to make the learned DNNs robust for different precision configuration during inference by adopting Lowest-Random-Highest bit-width co-training method. |
Ke Xu; Qiantai Feng; Xingyi Zhang; Dong Wang; |
505 | MemREIN: Rein The Domain Shift for Cross-Domain Few-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel framework, MemREIN, which considers Memorized, Restitution, and Instance Normalization for cross-domain few-shot learning. |
Yi Xu; Lichen Wang; Yizhou Wang; Can Qin; Yulun Zhang; Yun Fu; |
506 | Active Contrastive Set Mining for Robust Audio-Visual Instance Discrimination Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We argue that this assumption is rough, since the resulting contrastive sets have a large number of faulty negatives. In this paper, we overcome this limitation by proposing a novel Active Contrastive Set Mining (ACSM) that aims to mine the contrastive sets with informative and diverse negatives for robust AVID. |
Hanyu Xuan; Yihong Xu; Shuo Chen; Zhiliang Wu; Jian Yang; Yan Yan; Xavier Alameda-Pineda; |
507 | On The (In)Tractability of Reinforcement Learning for LTL Objectives Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we address the tractability of reinforcement learning for general LTL objectives from a theoretical perspective. |
Cambridge Yang; Michael L. Littman; Michael Carbin; |
508 | Towards Applicable Reinforcement Learning: Improving The Generalization and Sample Efficiency with Policy Ensemble Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To derive a robust and applicable RL algorithm, in this work, we design a simple but effective method named Ensemble Proximal Policy Optimization (EPPO), which learns ensemble policies in an end-to-end manner. |
Zhengyu Yang; Kan Ren; Xufang Luo; Minghuan Liu; Weiqing Liu; Jiang Bian; Weinan Zhang; Dongsheng Li; |
509 | Online ECG Emotion Recognition for Unknown Subjects Via Hypergraph-Based Transfer Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To tackle the problem, we propose a novel online cross-subject ECG emotion recognition method leveraging hypergraph-based online transfer learning (HOTL). |
Yalan Ye; Tongjie Pan; Qianhe Meng; Jingjing Li; Li Lu; |
510 | Towards Safe Reinforcement Learning Via Constraining Conditional Value-at-Risk Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address these issues, we first theoretically prove that the performance degradation under transition disturbance and observation disturbance depends on a novel metric of Value Function Range (VFR), which corresponds to the gap in the value function between the best state and the worst state. Based on the analysis, we adopt conditional value-at-risk (CVaR) as an assessment of risk and propose a novel reinforcement learning algorithm of CVaR-Proximal-Policy-Optimization (CPPO) which formalizes the risk-sensitive constrained optimization problem by keeping its CVaR under a given threshold. |
ChengYang Ying; Xinning Zhou; Hang Su; Dong Yan; Ning Chen; Jun Zhu; |
511 | EGCN: An Ensemble-based Learning Framework for Exploring Effective Skeleton-based Rehabilitation Exercise Assessment Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To advance the prior work, we propose a learning framework called Ensemble-based Graph Convolutional Network (EGCN) for skeleton-based rehabilitation exercise assessment. |
Bruce X.B. Yu; Yan Liu; Xiang Zhang; Gong Chen; Keith C.C. Chan; |
512 | Robust Weight Perturbation for Adversarial Training Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: A criterion that regulates the weight perturbation is therefore crucial for adversarial training. In this paper, we propose such a criterion, namely Loss Stationary Condition (LSC) for constrained perturbation. |
Chaojian Yu; Bo Han; Mingming Gong; Li Shen; Shiming Ge; Du Bo; Tongliang Liu; |
513 | Masked Feature Generation Network for Few-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a feature-augmentation approach called Masked Feature Generation Network (MFGN) for Few-Shot Learning (FSL), a challenging task that attempts to recognize the novel classes with a few visual instances for each class. |
Yunlong Yu; Dingyi Zhang; Zhong Ji; |
514 | Don’t Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: At the heart of this phenomenon is the diverged action distribution and high-variance value estimation in the face of augmented images. To alleviate this issue, we propose Task-aware Lipschitz Data Augmentation (TLDA) for visual RL, which explicitly identifies the task-correlated pixels with large Lipschitz constants, and only augments the task-irrelevant pixels for stability. |
Zhecheng Yuan; Guozheng Ma; Yao Mu; Bo Xia; Bo Yuan; Xueqian Wang; Ping Luo; Huazhe Xu; |
515 | Improved Pure Exploration in Linear Bandits with No-Regret Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose an explicitly implementable and provably order-optimal sample-complexity algorithm for best arm identification. |
Mohammadi Zaki; Avi Mohan; Aditya Gopalan; |
516 | Model-Based Offline Planning with Trajectory Pruning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose a new light-weighted model-based offline planning framework, namely MOPP, which tackles the dilemma between the restrictions of offline learning and high-performance planning. |
Xianyuan Zhan; Xiangyu Zhu; Haoran Xu; |
517 | Hyperbolic Knowledge Transfer with Class Hierarchy for Few-Shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our insight is, in the hyperbolic space, the hierarchy relation between classes can be well preserved by resorting to the exponential growth characters of hyperbolic volume, so that better knowledge transfer can be achieved for FSL. |
Baoquan Zhang; Hao Jiang; Shanshan Feng; Xutao Li; Yunming Ye; Rui Ye; |
518 | Fine-Tuning Graph Neural Networks Via Graph Topology Induced Optimal Transport Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we present a novel optimal transport-based fine-tuning framework called GTOT-Tuning, namely, Graph Topology induced Optimal Transport fine-Tuning, for GNN style backbones. |
Jiying Zhang; Xi Xiao; Long-Kai Huang; Yu Rong; Yatao Bian; |
519 | Hierarchical Diffusion Scattering Graph Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, these methods are prone to some problems such as over-smoothing because of the single-scale perspective field and the nature of low-pass filter. To address these limitations, we introduce diffusion scattering network (DSN) to exploit high-order patterns. |
Ke Zhang; Xinyan Pu; Jiaxing Li; Jiasong Wu; Huazhong Shu; Youyong Kong; |
520 | Penalized Proximal Policy Optimization for Safe Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose Penalized Proximal Policy Optimization (P3O), which solves the cumbersome constrained policy iteration via a single minimization of an equivalent unconstrained problem. |
Linrui Zhang; Li Shen; Long Yang; Shixiang Chen; Xueqian Wang; Bo Yuan; Dacheng Tao; |
521 | Next Point-of-Interest Recommendation with Inferring Multi-step Future Preferences Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Intuitively, users’ next POI visits may also be affected by their multi-step future behaviors, as users may often have activity planning in mind. To fill this gap, we propose a novel Context-aware Future Preference inference Recommender (CFPRec) to help infer user future preference in a self-ensembling manner. |
Lu Zhang; Zhu Sun; Ziqing Wu; Jie Zhang; Yew Soon Ong; Xinghua Qu; |
522 | Het2Hom: Representation of Heterogeneous Attributes Into Homogeneous Concept Spaces for Categorical-and-Numerical-Attribute Data Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Data sets composed of a mixture of categorical and numerical attributes (also called mixed data hereinafter) are common in real-world cluster analysis. However, insightful … |
Yiqun Zhang; Yiu-ming Cheung; An Zeng; |
523 | Learning Mixture of Neural Temporal Point Processes for Multi-dimensional Event Sequence Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To fill the gap, we propose Mixture of Neural Temporal Point Processes (NTPP-MIX), a general framework that can utilize many existing NTPPs for multi-dimensional event sequence clustering. |
Yunhao Zhang; Junchi Yan; Xiaolu Zhang; Jun Zhou; Xiaokang Yang; |
524 | Fusion Label Enhancement for Multi-Label Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel approach named Fusion Label Enhancement for Multi-label learning (FLEM) to effectively integrate the LE process and the training process. |
Xingyu Zhao; Yuexuan An; Ning Xu; Xin Geng; |
525 | Learning Mixtures of Random Utility Models with Features from Incomplete Preferences Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we consider RUMs with features and their mixtures, where each alternative has a vector of features, possibly different across agents. |
Zhibing Zhao; Ao Liu; Lirong Xia; |
526 | Unsupervised Voice-Face Representation Learning By Cross-Modal Prototype Contrast Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We present an approach to learn voice-face representations from the talking face videos, without any identity labels. |
Boqing Zhu; Kele Xu; Changjian Wang; Zheng Qin; Tao Sun; Huaimin Wang; Yuxing Peng; |
527 | RoSA: A Robust Self-Aligned Framework for Node-Node Graph Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a novel graph contrastive learning method named RoSA that focuses on utilizing non-aligned augmented views for node-level representation learning. |
Yun Zhu; Jianhao Guo; Fei Wu; Siliang Tang; |
528 | Multi-Constraint Deep Reinforcement Learning for Smooth Action Control Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: One of the crucial reasons for this issue is the inappropriate design of the reward in DRL. In this paper, to address this issue, we propose a novel way to incorporate the smoothness of actions in the reward. |
Guangyuan Zou; Ying He; F. Richard Yu; Longquan Chen; Weike Pan; Zhong Ming; |
529 | Subsequence-based Graph Routing Network for Capturing Multiple Risk Propagation Processes Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this study, we propose the subsequence-based graph routing network (S-GRN) for capturing the variant risk propagation processes among different time-series represented entities. |
Rui Cheng; Qing Li; |
530 | 3E-Solver: An Effortless, Easy-to-Update, and End-to-End Solver with Semi-Supervised Learning for Breaking Text-Based Captchas Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, these works still suffer from two main intrinsic limitations: (1) many labor costs are required to label the training data, and (2) the solver cannot be updated with unlabeled data to recognize captchas more accurately. In this paper, we present a novel solver using improved FixMatch for semi-supervised captcha recognition to tackle these problems. |
Xianwen Deng; Ruijie Zhao; Yanhao Wang; Libo Chen; Yijun Wang; Zhi Xue; |
531 | Placing Green Bridges Optimally, with Habitats Inducing Cycles Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Choosing the placement of wildlife crossings (i.e., green bridges) to reconnect animal species’ fragmented habitats is among the 17 goals towards sustainable development by the UN. We consider the following established model: Given a graph whose vertices represent the fragmented habitat areas and whose weighted edges represent possible green bridge locations, as well as the habitable vertex set for each species, find the cheapest set of edges such that each species’ habitat is connected. |
Maike Herkenrath; Till Fluschnik; Francesco Grothe; Leon Kellerhals; |
532 | Membership Inference Via Backdooring Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a novel membership inference approach inspired by the backdoor technology to address the said challenge. |
Hongsheng Hu; Zoran Salčić; Gillian Dobbie; Jinjun Chen; Lichao Sun; Xuyun Zhang; |
533 | A Universal PINNs Method for Solving Partial Differential Equations with A Point Source Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, they cannot be solved directly by conventional PINNs method due to the singularity brought by the Dirac delta function. In this paper, we propose a universal solution to tackle this problem by proposing three novel techniques. |
Xiang Huang; Hongsheng Liu; Beiji Shi; Zidong Wang; Kang Yang; Yang Li; Min Wang; Haotian Chu; Jing Zhou; Fan Yu; Bei Hua; Bin Dong; Lei Chen; |
534 | A Polynomial-time Decentralised Algorithm for Coordinated Management of Multiple Intersections Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Here, we focus on coordinating multiple intersections, and formulate the problem as a distributed constraint optimisation problem (DCOP). |
Tatsuya Iwase; Sebastian Stein; Enrico H. Gerding; Archie Chapman; |
535 | Multi-Agent Reinforcement Learning for Traffic Signal Control Through Universal Communication Method Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a universal communication form UniComm between intersections. |
Qize Jiang; Minhao Qin; Shengmin Shi; Weiwei Sun; Baihua Zheng; |
536 | Cumulative Stay-time Representation for Electronic Health Records in Medical Event Time Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The common time-series representation is indirect in extracting such information from EHR because it focuses on detailed dependencies between values in successive observations, not cumulative information. We propose a novel data representation for EHR called cumulative stay-time representation (CTR), which directly models such cumulative health conditions. |
Takayuki Katsuki; Kohei Miyaguchi; Akira Koseki; Toshiya Iwamori; Ryosuke Yanagiya; Atsushi Suzuki; |
537 | Self-Supervised Learning with Attention-based Latent Signal Augmentation for Sleep Staging with Limited Labeled Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Moreover, existing data augmentation techniques directly modify the original signal data, making it likely to lose important information. To mitigate these issues, we propose Self-Supervised Learning with Attention-aided Positive Pairs (SSLAPP). |
Harim Lee; Eunseon Seong; Dong-Kyu Chae; |
538 | Learning Curricula for Humans: An Empirical Study with Puzzles from The Witness Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we show how the Bootstrap learning system can be modified to learn curricula for humans in a puzzle domain. |
Levi H.S. Lelis; João G.G.V. Nova; Eugene Chen; Nathan R. Sturtevant; Carrie Demmans Epp; Michael Bowling; |
539 | Transformer-based Objective-reinforced Generative Adversarial Network to Generate Desired Molecules Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a transformer-based objective-reinforced generative adversarial network (TransORGAN) to generate molecules. |
Chen Li; Chikashige Yamanaka; Kazuma Kaitoh; Yoshihiro Yamanishi; |
540 | Towards Controlling The Transmission of Diseases: Continuous Exposure Discovery Over Massive-Scale Moving Objects Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our problem targets a variety of applications, including but not limited to disease control, epidemic pre-warning, information spreading, and co-movement mining. To answer this problem, we develop an exact group processing algorithm with optimization strategies. |
Ke Li; Lisi Chen; Shuo Shang; Haiyan Wang; Yang Liu; Panos Kalnis; Bin Yao; |
541 | Distilling Governing Laws and Source Input for Dynamical Systems from Videos Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper introduces an end-to-end unsupervised deep learning framework to uncover the explicit governing equations of dynamics presented by moving object(s), based on recorded videos. |
Lele Luan; Yang Liu; Hao Sun; |
542 | Monolith to Microservices: Representing Application Software Through Heterogeneous Graph Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: But the challenges associated with the separation of functional modules, slows down the migration of a monolithic code into microservices. In this work, we propose a representation learning based solution to tackle this problem. |
Alex Mathai; Sambaran Bandyopadhyay; Utkarsh Desai; Srikanth Tamilselvam; |
543 | Learn Continuously, Act Discretely: Hybrid Action-Space Reinforcement Learning For Optimal Execution Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: So we need continuous control for generalization and discrete control for specialization. To this end, we propose a hybrid RL method to combine the advantages of both of them. |
Feiyang Pan; Tongzhe Zhang; Ling Luo; Jia He; Shuoling Liu; |
544 | Communicative Subgraph Representation Learning for Multi-Relational Inductive Drug-Gene Interaction Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In addition, existing methods either heavily rely on high-quality domain features or are intrinsically transductive, which limits the capacity of models to generalize to drugs/genes that lack external information or are unseen during the training process. To address these problems, we propose a novel Communicative Subgraph representation learning for Multi-relational Inductive drug-Gene interactions prediction (CoSMIG), where the predictions of drug-gene relations are made through subgraph patterns, and thus are naturally inductive for unseen drugs/genes without retraining or utilizing external domain features. |
Jiahua Rao; Shuangjia Zheng; Sijie Mai; Yuedong Yang; |
545 | FOGS: First-Order Gradient Supervision with Learning-based Graph for Traffic Flow Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To solve the above-mentioned problems, in this paper, we propose a novel learning-based method to learn a spatial-temporal correlation graph, which could make good use of the traffic flow data. |
Xuan Rao; Hao Wang; Liang Zhang; Jing Li; Shuo Shang; Peng Han; |
546 | Offline Vehicle Routing Problem with Online Bookings: A Novel Problem Formulation with Applications to Paratransit Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This problem is very challenging computationally since it faces the complexity of considering large sets of requests—similar to offline VRPs—but must abide by strict constraints on running time—similar to online VRPs. To solve this problem, we propose a novel computational approach, which combines an anytime algorithm with a learning-based policy for real-time decisions. |
Amutheezan Sivagnanam; Salah Uddin Kadir; Ayan Mukhopadhyay; Philip Pugliese; Abhishek Dubey; Samitha Samaranayake; Aron Laszka; |
547 | Local Differential Privacy Meets Computational Social Choice – Resilience Under Voter Deletion Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The goal of this paper is to provide a quantitative study on the effect of adopting LDP mechanisms on a voting system. |
Liangde Tao; Lin Chen; Lei Xu; Weidong Shi; |
548 | Private Stochastic Convex Optimization and Sparse Learning with Heavy-tailed Data Revisited Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we revisit the problem of Differentially Private Stochastic Convex Optimization (DP-SCO) with heavy-tailed data, where the gradient of the loss function has bounded moments. |
Youming Tao; Yulian Wu; Xiuzhen Cheng; Di Wang; |
549 | Exploring The Vulnerability of Deep Reinforcement Learning-based Emergency Control for Low Carbon Power Systems Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Decarbonization of global power systems significantly increases the operational uncertainty and modeling complexity that drive the necessity of widely exploiting cutting-edge Deep … |
Xu Wan; Lanting Zeng; Mingyang Sun; |
550 | Heterogeneous Interactive Snapshot Network for Review-Enhanced Stock Profiling and Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel heterogeneous interactive snapshot network for stock profiling and recommendation. |
Heyuan Wang; Tengjiao Wang; Shun Li; Shijie Guan; Jiayi Zheng; Wei Chen; |
551 | Adaptive Long-Short Pattern Transformer for Stock Investment Selection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel Adaptive Long-Short Pattern Transformer (ALSP-TF) for stock ranking in terms of expected returns. |
Heyuan Wang; Tengjiao Wang; Shun Li; Jiayi Zheng; Shijie Guan; Wei Chen; |
552 | Bridging The Gap Between Reality and Ideality of Entity Matching: A Revisting and Benchmark Re-Constrcution Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: While current deep learning-based methods achieve very impressive performance on standard EM benchmarks, their real-world application performance is much frustrating. In this paper, we highlight that such the gap between reality and ideality stems from the unreasonable benchmark construction process, which is inconsistent with the nature of entity matching and therefore leads to biased evaluations of current EM approaches. |
Tianshu Wang; Hongyu Lin; Cheng Fu; Xianpei Han; Le Sun; Feiyu Xiong; Hui Chen; Minlong Lu; Xiuwen Zhu; |
553 | Learnability of Competitive Threshold Models Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we study the learnability of the competitive threshold model from a theoretical perspective. |
Yifan Wang; Guangmo Tong; |
554 | Data-Efficient Backdoor Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we formulate improving the poisoned data efficiency by the selection as an optimization problem and propose a Filtering-and-Updating Strategy (FUS) to solve it. |
Pengfei Xia; Ziqiang Li; Wei Zhang; Bin Li; |
555 | TinyLight: Adaptive Traffic Signal Control on Devices with Extremely Limited Resources Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose TinyLight, the first DRL-based ATSC model that is designed for devices with extremely limited resources. |
Dong Xing; Qian Zheng; Qianhui Liu; Gang Pan; |
556 | ARCANE: An Efficient Architecture for Exact Machine Unlearning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose an exact unlearning architecture called ARCANE. |
Haonan Yan; Xiaoguang Li; Ziyao Guo; Hui Li; Fenghua Li; Xiaodong Lin; |
557 | A Smart Trader for Portfolio Management Based on Normalizing Flows Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we study a new kind of portfolio problem, named trading point aware portfolio optimization (TPPO), which aims to obtain excess intraday profit by deciding the portfolio weights and their trading points simultaneously based on microscopic information. |
Mengyuan Yang; Xiaolin Zheng; Qianqiao Liang; Bing Han; Mengying Zhu; |
558 | Temporality Spatialization: A Scalable and Faithful Time-Travelling Visualization for Deep Classifier Training Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose TimeVis, a novel time-travelling visualization solution for deep classifiers. |
Xianglin Yang; Yun Lin; Ruofan Liu; Jin Song Dong; |
559 | Post-processing of Differentially Private Data: A Fairness Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In the first setting, the paper proposes tight bounds on the unfairness for traditional post-processing mechanisms, giving a unique tool to decision makers to quantify the disparate impacts introduced by their release. |
Keyu Zhu; Ferdinando Fioretto; Pascal Van Hentenryck; |
560 | Enhancing Entity Representations with Prompt Learning for Biomedical Entity Linking Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Yet, the ambiguity challenge that the same word under different contexts may refer to distinct entities is usually ignored. To address this challenge, we propose a two-stage linking algorithm to enhance the entity representations based on prompt learning. |
Tiantian Zhu; Yang Qin; Qingcai Chen; Baotian Hu; Yang Xiang; |
561 | Aspect-based Sentiment Analysis with Opinion Tree Generation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this study, we introduce an Opinion Tree Generation task, which aims to jointly detect all sentiment elements in a tree. |
Xiaoyi Bao; Wang Zhongqing; Xiaotong Jiang; Rong Xiao; Shoushan Li; |
562 | Speaker-Guided Encoder-Decoder Framework for Emotion Recognition in Conversation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Besides, we propose a Speaker-Guided Encoder-Decoder (SGED) framework for ERC, which fully exploits speaker information for the decoding of emotion. |
Yinan Bao; Qianwen Ma; Lingwei Wei; Wei Zhou; Songlin Hu; |
563 | Learning Meta Word Embeddings By Unsupervised Weighted Concatenation of Source Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We show that weighted concatenation can be seen as a spectrum matching operation between each source embedding and the meta-embedding, minimising the pairwise inner-product loss. Following this theoretical analysis, we propose two \emph{unsupervised} methods to learn the optimal concatenation weights for creating meta-embeddings from a given set of source embeddings. |
Danushka Bollegala; |
564 | PCVAE: Generating Prior Context for Dialogue Response Generation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, the conventional used continual latent variables in CVAE are more likely to generate generic rather than distinct and specific responses. To resolve this problem, we introduce a novel discrete variable called prior context which enables the generation of favorable responses. |
Zefeng Cai; Zerui Cai; |
565 | Towards Joint Intent Detection and Slot Filling Via Higher-order Attention Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, we think the conventional attention can only capture the first-order feature interaction between two tasks and is insufficient. To address this issue, we propose a unified BiLinear attention block, which leverages bilinear pooling to synchronously explore both the contextual and channel-wise bilinear attention distributions to capture the second-order interactions between the input intent and slot features. |
Dongsheng Chen; Zhiqi Huang; Xian Wu; Shen Ge; Yuexian Zou; |
566 | Effective Graph Context Representation for Document-level Machine Translation Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Document-level neural machine translation (DocNMT) universally encodes several local sentences or the entire document. Thus, DocNMT does not consider the relevance of … |
Kehai Chen; Muyun Yang; Masao Utiyama; Eiichiro Sumita; Rui Wang; Min Zhang; |
567 | DictBERT: Dictionary Description Knowledge Enhanced Language Model Pre-training Via Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address the challenge, we propose DictBERT, a novel approach that enhances PLMs with dictionary knowledge which is easier to acquire than knowledge graph (KG). |
Qianglong Chen; Feng-Lin Li; Guohai Xu; Ming Yan; Ji Zhang; Yin Zhang; |
568 | Interpretable AMR-Based Question Decomposition for Multi-hop Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Most existing approaches cannot provide an interpretable reasoning process to illustrate how these models arrive at an answer. In this paper, we propose a Question Decomposition method based on Abstract Meaning Representation (QDAMR) for multi-hop QA, which achieves interpretable reasoning by decomposing a multi-hop question into simpler subquestions and answering them in order. |
Zhenyun Deng; Yonghua Zhu; Yang Chen; Michael Witbrock; Patricia Riddle; |
569 | Interactive Information Extraction By Semantic Information Graph Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To overcome the shortages, we propose an Interactive Information Extraction (InterIE) model based on a novel Semantic Information Graph (SIG). |
Siqi Fan; Yequan Wang; Jing Li; Zheng Zhang; Shuo Shang; Peng Han; |
570 | Global Inference with Explicit Syntactic and Discourse Structures for Dialogue-Level Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we investigate a novel dialogue-level mixed dependency graph (D2G) and an argument reasoning graph (ARG) for DiaRE with a global relation reasoning mechanism. |
Hao Fei; Jingye Li; Shengqiong Wu; Chenliang Li; Donghong Ji; Fei Li; |
571 | Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we investigate the integration of a latent graph for CSRL. |
Hao Fei; Shengqiong Wu; Meishan Zhang; Yafeng Ren; Donghong Ji; |
572 | Inheriting The Wisdom of Predecessors: A Multiplex Cascade Framework for Unified Aspect-based Sentiment Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: So far, aspect-based sentiment analysis (ABSA) has involved with total seven subtasks, in which, however the interactions among them have been left unexplored sufficiently. This work presents a novel multiplex cascade framework for unified ABSA and maintaining such interactions. |
Hao Fei; Fei Li; Chenliang Li; Shengqiong Wu; Jingye Li; Donghong Ji; |
573 | Logically Consistent Adversarial Attacks for Soft Theorem Provers Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Recent efforts within the AI community have yielded impressive results towards “soft theorem proving” over natural language sentences using language models. We propose a novel, generative adversarial framework for probing and improving these models’ reasoning capabilities. |
Alexander Gaskell; Yishu Miao; Francesca Toni; Lucia Specia; |
574 | Leveraging The Wikipedia Graph for Evaluating Word Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, explicitly annotating word pairs with similarity scores by surveying humans is expensive. We tackle this problem by formulating a similarity measure that is based on an agent for routing the Wikipedia hyperlink graph. |
Joachim Giesen; Paul Kahlmeyer; Frank Nussbaum; Sina Zarrieß; |
575 | Fallacious Argument Classification in Political Debates Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Fallacies play a prominent role in argumentation since antiquity due to their contribution to argumentation in critical thinking education. Their role is even more crucial … |
Pierpaolo Goffredo; Shohreh Haddadan; Vorakit Vorakitphan; Elena Cabrio; Serena Villata; |
576 | Improving Few-Shot Text-to-SQL with Meta Self-Training Via Column Specificity Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a Meta Self-Training text-to-SQL (MST-SQL) method to solve the problem. |
Xinnan Guo; Yongrui Chen; Guilin Qi; Tianxing Wu; Hao Xu; |
577 | FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper proposes FastDiff, a fast conditional diffusion model for high-quality speech synthesis. |
Rongjie Huang; Max W. Y. Lam; Jun Wang; Dan Su; Dong Yu; Yi Ren; Zhou Zhao; |
578 | MuiDial: Improving Dialogue Disentanglement with Intent-Based Mutual Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Inspired by mutual leaning, we propose MuiDial, a novel dialogue disentanglement model, to exploit the intent of each utterance and feed the intent to a mutual learning U2U-U2T disentanglement model. |
Ziyou Jiang; Lin Shi; Celia Chen; Fangwen Mu; Yumin Zhang; Qing Wang; |
579 | AdMix: A Mixed Sample Data Augmentation Method for Neural Machine Translation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel data augmentation approach for NMT, which is independent of any additional training data. |
Chang Jin; Shigui Qiu; Nini Xiao; Hao Jia; |
580 | Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To alleviate the side-effect of low-quality pseudo-labeled data during self-training, we propose a novel method called Curriculum-Based Self-Training (CBST) to effectively leverage unlabeled data in a rearranged order determined by the difficulty of text generation. |
Pei Ke; Haozhe Ji; Zhenyu Yang; Yi Huang; Junlan Feng; Xiaoyan Zhu; Minlie Huang; |
581 | Deexaggeration Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce a new task in hyperbole processing, deexaggeration, which concerns the recovery of the meaning of what is being exaggerated in a hyperbolic sentence in the form of a structured representation. |
Li Kong; Chuanyi Li; Vincent Ng; |
582 | Taylor, Can You Hear Me Now? A Taylor-Unfolding Framework for Monaural Speech Enhancement Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Inspired by Taylor’s approximation theory, we propose an interpretable decoupling-style SE framework, which disentangles the complex spectrum recovery into two separate optimization problems i.e., magnitude and complex residual estimation. |
Andong Li; Shan You; Guochen Yu; Chengshi Zheng; Xiaodong Li; |
583 | FastRE: Towards Fast Relation Extraction with Convolutional Encoder and Improved Cascade Binary Tagging Framework Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: The main efficiency bottleneck is that these methods use a Transformer-based pre-trained language model for encoding, which heavily affects the training speed and inference speed. To address this issue, we propose a fast relation extraction model (FastRE) based on convolutional encoder and improved cascade binary tagging framework. |
Guozheng Li; Xu Chen; Peng Wang; Jiafeng Xie; Qiqing Luo; |
584 | Neutral Utterances Are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledge Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we build conversations as graphs to overcome implicit contextual modelling of the original entailment style. |
Jiangnan Li; Fandong Meng; Zheng Lin; Rui Liu; Peng Fu; Yanan Cao; Weiping Wang; Jie Zhou; |
585 | Domain-Adaptive Text Classification with Structured Knowledge from Unlabeled Data Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a novel method, called Domain Adaptation with Structured Knowledge (DASK), to enhance domain adaptation by exploiting word-level semantic relationships. |
Tian Li; Xiang Chen; Zhen Dong; Kurt Keutzer; Shanghang Zhang; |
586 | Parameter-Efficient Sparsity for Large Language Models Fine-Tuning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: While most research focuses on how to accurately retain appropriate weights while maintaining the performance of the compressed model, there are challenges in the computational overhead and memory footprint of sparse training when compressing large-scale language models. To address this problem, we propose a Parameter-efficient Sparse Training (PST) method to reduce the number of trainable parameters during sparse-aware training in downstream tasks. |
Yuchao Li; Fuli Luo; Chuanqi Tan; Mengdi Wang; Songfang Huang; Shen Li; Junjie Bai; |
587 | Explicit Alignment Learning for Neural Machine Translation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Thus, we propose two approaches an explicit alignment learning approach, in which we further remove the need for the additional alignment model, and perform embedding mixup with the alignment based on encoder–decoder attention weights in the NMT model. |
Zuchao Li; Hai Zhao; Fengshun Xiao; Masao Utiyama; Eiichiro Sumita; |
588 | Lyra: A Benchmark for Turducken-Style Code Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Since a declarative language is typically embedded in an imperative language (i.e., the turducken-style programming) in real-world software development, the promising results on declarative languages can hardly lead to significant reduction of manual software development efforts. In this paper, we define a new code generation task: given a natural language comment, this task aims to generate a program in a base imperative language with an embedded declarative language. |
Qingyuan Liang; Zeyu Sun; Qihao Zhu; Wenjie Zhang; Lian Yu; Yingfei Xiong; Lu Zhang; |
589 | CUP: Curriculum Learning Based Prompt Tuning for Implicit Event Argument Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a Curriculum learning based Prompt tuning (CUP) approach, which resolves implicit EAE by four learning stages. |
Jiaju Lin; Qin Chen; Jie Zhou; Jian Jin; Liang He; |
590 | Low-Resource NER By Data Augmentation With Prompting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a new data augmentation method for low-resource NER, by eliciting knowledge from BERT with prompting strategies. |
Jian Liu; Yufeng Chen; Jinan Xu; |
591 | Generating A Structured Summary of Numerous Academic Papers: Dataset and Method Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To organize the diverse content from dozens of input documents and ensure the efficiency of processing long text sequences, we propose a summarization method named category-based alignment and sparse transformer (CAST). |
Shuaiqi LIU; Jiannong Cao; Ruosong Yang; Zhiyuan Wen; |
592 | “My Nose Is Running.” “Are You Also Coughing?”: Building A Medical Diagnosis Agent with Interpretable Inquiry Logics Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we explore how to bring interpretability to data-driven DSMD. |
Wenge Liu; Yi Cheng; Hao Wang; Jianheng Tang; Yafei Liu; Ruihui Zhao; Wenjie Li; Yefeng Zheng; Xiaodan Liang; |
593 | Abstract Rule Learning for Paraphrase Generation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, the current neural models are black boxes and are prone to make local modifications to the inputs. In this work, we combine these two approaches into RULER, a novel approach that performs abstract rule learning for paraphrasing. |
Xianggen Liu; Wenqiang Lei; Jiancheng Lv; Jizhe Zhou; |
594 | Graph-based Dynamic Word Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To tackle the aforementioned challenges, we propose a graph-based dynamic word embedding (GDWE) model, which focuses on capturing the semantic drift of words continually. |
Yuyin Lu; Xin Cheng; Ziran Liang; Yanghui Rao; |
595 | Searching for Optimal Subword Tokenization in Cross-domain NER Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we shed new light on cross-domain NER by introducing a subword-level solution, X-Piece, for input word-level distribution shift in NER. |
Ruotian Ma; Yiding Tan; Xin Zhou; Xuanting Chen; Di Liang; Sirui Wang; Wei Wu; Tao Gui; |
596 | Prompting to Distill: Boosting Data-Free Knowledge Distillation Via Reinforced Prompt Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Prior DFKD approaches, however, have largely relied on hand-crafted priors of the target data distribution for the reconstruction, which can be inevitably biased and often incompetent to capture the intrinsic distributions. To address this problem, we propose a prompt-based method, termed as PromptDFD, that allows us to take advantage of learned language priors, which effectively harmonizes the synthetic sentences to be semantically and grammatically correct. |
Xinyin Ma; Xinchao Wang; Gongfan Fang; Yongliang Shen; Weiming Lu; |
597 | Variational Learning for Unsupervised Knowledge Grounded Dialogs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Models such as RAG, marginalize the document probabilities over the documents retrieved from the index to define the log-likelihood loss function which is optimized end-to-end. In this paper, we develop a variational approach to the above technique wherein, we instead maximize the Evidence Lower bound (ELBO). |
Mayank Mishra; Dhiraj Madan; Gaurav Pandey; Danish Contractor; |
598 | Enhancing Text Generation Via Multi-Level Knowledge Aware Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we leverage event-level knowledge to enhance text generation. |
Feiteng Mu; Wenjie Li; |
599 | Automatic Noisy Label Correction for Fine-Grained Entity Typing Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a novel approach to automatically correct noisy labels for FET without external resources. |
Weiran Pan; Wei Wei; Feida Zhu; |
600 | Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a Global-to-Local Hierarchical Graph Network to capture the multi-source information (global cause, local intentions and dialog history) and model hierarchical relationships between them, which consists of a multi-source encoder, a hierarchical graph reasoner, and a global-guide decoder. |
Wei Peng; Yue Hu; Luxi Xing; Yuqiang Xie; Yajing Sun; Yunpeng Li; |
601 | Document-level Relation Extraction Via Subgraph Reasoning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel subgraph reasoning (SGR) framework for document-level relation extraction. |
Xingyu Peng; Chong Zhang; Ke Xu; |
602 | Document-level Event Factuality Identification Via Reinforced Multi-Granularity Hierarchical Attention Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, previous studies relied on annotated information and did not filter irrelevant and noisy texts. Therefore, this paper proposes a novel end-to-end model, i.e., Reinforced Multi-Granularity Hierarchical Attention Network (RMHAN), which can learn information at different levels of granularity from tokens and sentences hierarchically. |
Zhong Qian; Peifeng Li; Qiaoming Zhu; Guodong Zhou; |
603 | BiFSMN: Binary Neural Network for Keyword Spotting Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we present BiFSMN, an accurate and extreme-efficient binary neural network for KWS. |
Haotong Qin; Xudong Ma; Yifu Ding; Xiaoyang Li; Yang Zhang; Yao Tian; Zejun Ma; Jie Luo; Xianglong Liu; |
604 | Training Naturalized Semantic Parsers with Very Little Data Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To better leverage that pretraining, recent work has explored a reformulation of semantic parsing whereby the output sequences are themselves natural language sentences, but in a controlled fragment of natural language. |
Subendhu Rongali; Konstantine Arkoudas; Melanie Rubino; Wael Hamza; |
605 | Relational Triple Extraction: One Step Is Enough Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To solve the problem, in this paper, we introduce a fresh perspective to revisit the triple extraction task and propose a simple but effective model, named DirectRel. |
Yu-Ming Shang; Heyan Huang; Xin Sun; Wei Wei; Xian-Ling Mao; |
606 | A Unified Strategy for Multilingual Grammatical Error Correction with Pre-trained Cross-Lingual Language Model Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a generic and language-independent strategy for multilingual GEC, which can train a GEC system effectively for a new non-English language with only two easy-to-access resources: 1) a pre-trained cross-lingual language model (PXLM) and 2) parallel translation data between English and the language. |
Xin Sun; Tao Ge; Shuming Ma; Jingjing Li; Furu Wei; Houfeng Wang; |
607 | On Tracking Dialogue State By Inheriting Slot Values in Mentioned Slot Pools Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This study designed a model with a mentioned slot pool (MSP) to tackle the update problem. |
Zhoujian Sun; Zhengxing Huang; Nai Ding; |
608 | Towards Discourse-Aware Document-Level Neural Machine Translation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we aim at incorporating the coherence information hidden within the RST-style discourse structure into machine translation. |
Xin Tan; Longyin Zhang; Fang Kong; Guodong Zhou; |
609 | Learning By Interpreting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper introduces a novel way of enhancing NLP prediction accuracy by incorporating model interpretation insights. |
Xuting Tang; Abdul Rafae Khan; Shusen Wang; Jia Xu; |
610 | Robust Fine-tuning Via Perturbation and Interpolation from In-batch Instances Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a simple yet effective fine-tuning method called Match-Tuning to force the PLMs to be more robust. |
Shoujie Tong; Qingxiu Dong; Damai Dai; Yifan Song; Tianyu Liu; Baobao Chang; Zhifang Sui; |
611 | MGAD: Learning Descriptional Representation Distilled from Distributional Semantics for Unseen Entities Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, these methods lead to poor representations for unseen entities since they rely on a multitude of occurrences for each entity to enable accurate representations. To address this issue, we propose to learn enhanced descriptional representations for unseen entities by distilling knowledge from distributional semantics into descriptional embeddings. |
Yuanzheng Wang; Xueqi Cheng; Yixing Fan; Xiaofei Zhu; Huasheng Liang; Qiang Yan; Jiafeng Guo; |
612 | Unsupervised Context Aware Sentence Representation Pretraining for Multi-lingual Dense Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we present a simple but effective monolingual pretraining task called contrastive context prediction (CCP) to learn sentence representation by modeling sentence level contextual relation. |
Ning Wu; Yaobo Liang; Houxing Ren; Linjun Shou; Nan Duan; Ming Gong; Daxin Jiang; |
613 | Propose-and-Refine: A Two-Stage Set Prediction Network for Nested Named Entity Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Besides, span-based methods have trouble predicting long entities due to limited span enumeration length. To mitigate these issues, we present the Propose-and-Refine Network (PnRNet), a two-stage set prediction network for nested NER. |
Shuhui Wu; Yongliang Shen; Zeqi Tan; Weiming Lu; |
614 | Neural Subgraph Explorer: Reducing Noisy Information Via Target-oriented Syntax Graph Pruning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, we discover that existing syntax-based models suffer from two issues: noisy information aggregation and loss of distant correlations. In this paper, we propose a novel model termed Neural Subgraph Explorer, which (1) reduces the noisy information via pruning target-irrelevant nodes on the syntax graph; (2) introduces beneficial first-order connections between the target and its related words into the obtained graph. |
Bowen Xing; Ivor Tsang; |
615 | TaxoPrompt: A Prompt-based Generation Method with Taxonomic Context for Self-Supervised Taxonomy Expansion Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose TaxoPrompt, a framework that learns the global structure by prompt tuning with taxonomic context. |
Hongyuan Xu; Yunong Chen; Zichen Liu; Yanlong Wen; Xiaojie Yuan; |
616 | Robust Interpretable Text Classification Against Spurious Correlations Using AND-rules with Negation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we employ a rule-based architecture called Tsetlin Machine (TM) that learns both simple and complex correlations by ANDing features and their negations. |
Rohan Kumar Yadav; Lei Jiao; Ole-Christoffer Granmo; Morten Goodwin; |
617 | Diversity Features Enhanced Prototypical Network for Few-shot Intent Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose an effective Diversity Features Enhanced Prototypical Network (DFEPN) to enhance diversity features for novel intents by fully exploiting the diversity of known intent samples. |
Fengyi Yang; Xi Zhou; Yi Wang; Abibulla Atawulla; Ran Bi; |
618 | UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a novel method, named as Unified Multilingual Multiple teacher-student Model for NMT (UM4). |
Jian Yang; Yuwei Yin; Shuming Ma; Dongdong Zhang; Shuangzhi Wu; Hongcheng Guo; Zhoujun Li; Furu Wei; |
619 | High-resource Language-specific Training for Multilingual Neural Machine Translation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose the multilingual translation model with the high-resource language-specific training (HLT-MT) to alleviate the negative interference, which adopts the two-stage training with the language-specific selection mechanism. |
Jian Yang; Yuwei Yin; Shuming Ma; Dongdong Zhang; Zhoujun Li; Furu Wei; |
620 | SyntaSpeech: Syntax-Aware Generative Adversarial Text-to-Speech Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, current NAR-TTS models usually use phoneme sequence as input and thus cannot understand the tree-structured syntactic information of the input sequence, which hurts the prosody modeling. To this end, we propose SyntaSpeech, a syntax-aware and light-weight NAR-TTS model, which integrates tree-structured syntactic information into the prosody modeling modules in PortaSpeech. |
Zhenhui Ye; Zhou Zhao; Yi Ren; Fei Wu; |
621 | Clickbait Detection Via Contrastive Variational Modelling of Text and Label Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Inspired by related pedagogy theories that learning to write can promote comprehension ability, we propose a novel Contrastive Variational Modelling (CVM) framework to exploit the labelled data better. |
Xiaoyuan Yi; Jiarui Zhang; Wenhao Li; Xiting Wang; Xing Xie; |
622 | Targeted Multimodal Sentiment Classification Based on Coarse-to-Fine Grained Image-Target Matching Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Existing methods to TMSC failed to explicitly capture both coarse-grained and fine-grained image-target matching, including 1) the relevance between the image and the target and 2) the alignment between visual objects and the target. To tackle this issue, we propose a new multi-task learning architecture named coarse-to-fine grained Image-Target Matching network (ITM), which jointly performs image-target relevance classification, object-target alignment, and targeted sentiment classification. |
Jianfei Yu; Jieming Wang; Rui Xia; Junjie Li; |
623 | Stage-wise Stylistic Headline Generation: Style Generation and Summarized Content Insertion Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, this inevitably suffers from error propagation. Therefore, to unify the two sub-tasks and explicitly decompose style-relevant attributes and summarize content, we propose an end-to-end stage-wise SHG model containing the style generation component and the content insertion component, where the former generates stylistic-relevant intermediate outputs and the latter receives these outputs then inserts the summarized content. |
Jiaao Zhan; Yang Gao; Yu Bai; Qianhui Liu; |
624 | Position-aware Joint Entity and Relation Extraction with Attention Mechanism Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In our work, we propose a joint entity and relation extraction model with an attention mechanism and position-attentive markers. |
Chenglong Zhang; Shuyong Gao; Haofen Wang; Wenqiang Zhang; |
625 | EditSinger: Zero-Shot Text-Based Singing Voice Editing System with Diverse Prosody Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we propose EditSinger, which is a novel singing voice editing model with specially designed diverse prosody modules to overcome the challenges above. |
Lichao Zhang; Zhou Zhao; Yi Ren; Liqun Deng; |
626 | “Think Before You Speak”: Improving Multi-Action Dialog Policy By Planning Single-Action Dialogs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: While interactive learning and reinforcement learning algorithms can be applied to incorporate external data sources of real users and user simulators, they take significant manual effort to build and suffer from instability. To address these issues, we propose Planning Enhanced Dialog Policy (PEDP), a novel multi-task learning framework that learns single-action dialog dynamics to enhance multi-action prediction. |
Shuo Zhang; Junzhou Zhao; Pinghui Wang; Yu Li; Yi Huang; Junlan Feng; |
627 | Charge Prediction By Constitutive Elements Matching of Crimes Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we propose a novel method named Constitutive Elements-guided Charge Prediction (CECP). |
Jie Zhao; Ziyu Guan; Cai Xu; Wei Zhao; Enze Chen; |
628 | CauAIN: Causal Aware Interaction Network for Emotion Recognition in Conversations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose Causal Aware Interaction Network (CauAIN) to thoroughly understand the conversational context with the help of emotion cause detection. |
Weixiang Zhao; Yanyan Zhao; Xin Lu; |
629 | Reasoning Over Hybrid Chain for Table-and-Text Open Domain Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a ChAin-centric Reasoning and Pre-training framework (CARP). |
Wanjun Zhong; Junjie Huang; Qian Liu; Ming Zhou; Jiahai Wang; Jian Yin; Nan Duan; |
630 | None Class Ranking Loss for Document-Level Relation Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This ignores the context of entity pairs and the label correlations between the none class and pre-defined classes, leading to sub-optimal predictions. To address this problem, we propose a new multi-label loss that encourages large margins of label confidence scores between each pre-defined class and the none class, which enables captured label correlations and context-dependent thresholding for label prediction. |
Yang Zhou; Wee Sun Lee; |
631 | Grape: Grammar-Preserving Rule Embedding Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we make the first attempt to learn a grammar-preserving rule embedding. |
Qihao Zhu; Zeyu Sun; Wenjie Zhang; Yingfei Xiong; Lu Zhang; |
632 | Efficient Document-level Event Extraction Via Pseudo-Trigger-aware Pruned Complete Graph Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In contrast to the previous studies, we propose a fast and lightweight model named as PTPCG. |
Tong Zhu; Xiaoye Qu; Wenliang Chen; Zhefeng Wang; Baoxing Huai; Nicholas Yuan; Min Zhang; |
633 | Contrastive Graph Transformer Network for Personality Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we construct a fully-connected post graph for each user and develop a novel Contrastive Graph Transformer Network model (CGTN) which distills potential labels of the graphs based on both labeled and unlabeled data. |
Yangfu Zhu; Linmei Hu; Xinkai Ge; Wanrong Peng; Bin Wu; |
634 | Explaining The Behaviour of Hybrid Systems with PDDL+ Planning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The aim of this work is to explain the observed behaviour of a hybrid system (HS). |
Diego Aineto; Eva Onaindia; Miquel Ramirez; Enrico Scala; Ivan Serina; |
635 | Online Bin Packing with Predictions Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we study the online variant of the problem, in which a sequence of items of various sizes must be placed into a minimum number of bins of uniform capacity. |
Spyros Angelopoulos; Shahin Kamali; Kimia Shadkami; |
636 | Scheduling with Untrusted Predictions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we study classic scheduling problems under the learning augmented setting. |
Evripidis Bampis; Konstantinos Dogeas; Alexander Kononov; Giorgio Lucarelli; Fanny Pascual; |
637 | Adaptive Information Belief Space Planning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We formulate an approximation, namely an abstract observation model, that uses an aggregation scheme to alleviate computational costs. |
Moran Barenboim; Vadim Indelman; |
638 | Tight Bounds for Hybrid Planning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The formalism combining Hierarchical Task Network (HTN) planning with these links known from Partial Order Causal Link (POCL) planning is often referred to as hybrid planning. In this paper we study the computational complexity of such hybrid planning problems. |
Pascal Bercher; Songtuan Lin; Ron Alford; |
639 | Planning with Qualitative Action-Trajectory Constraints in PDDL Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: In automated planning the ability of expressing constraints on the structure of the desired plans is important to deal with solution quality, as well as to express control … |
Luigi Bonassi; Alfonso Emilio Gerevini; Enrico Scala; |
640 | Shared Autonomy Systems with Stochastic Operator Models Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a framework for stochastic operators in shared autonomy systems (SO-SAS), where we represent operators using rich, partially observable models. |
Clarissa Costen; Marc Rigter; Bruno Lacerda; Nick Hawes; |
641 | Explaining Soft-Goal Conflicts Through Constraint Relaxations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: A baseline is to simply loop over all relaxed tasks and compute the conflicts for each separately. We improve over this by two algorithms that leverage information — conflicts, reachable states — across relaxed tasks. |
Rebecca Eifler; Jeremy Frank; Jörg Hoffmann; |
642 | Online Planning in POMDPs with Self-Improving Simulators Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Given the original simulator of the environment, which may be computationally very demanding, we propose to learn online an approximate but much faster simulator that improves over time. |
Jinke He; Miguel Suau; Hendrik Baier; Michael Kaisers; Frans A. Oliehoek; |
643 | An Efficient Approach to Data Transfer Scheduling for Long Range Space Exploration Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we revisit the problem of assigning priorities to data transfers in order to maximize safety margin of onboard memory. |
Emmanuel Hebrard; Christian Artigues; Pierre Lopez; Arnaud Lusson; Steve Chien; Adrien Maillard; Gregg Rabideau; |
644 | General Optimization Framework for Recurrent Reachability Objectives Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We consider the mobile robot path planning problem for a class of recurrent reachability objectives. |
David Klaska; Antonin Kucera; Vit Musil; Vojtech Rehak; |
645 | Offline Time-Independent Multi-Agent Path Planning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We present solution conditions, computational complexity, solvers, and robotic applications. |
Keisuke Okumura; François Bonnet; Yasumasa Tamura; Xavier Défago; |
646 | On The Computational Complexity of Model Reconciliations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: While the framework has been extended to multiple settings since its introduction for classical planning problems, there is little agreement on the computational complexity of generating minimal model reconciliation explanations in the basic setting. In this paper, we address this lacuna by introducing a decision-version of the model-reconciliation explanation generation problem and we show that it is Sigma-2-P Complete. |
Sarath Sreedharan; Pascal Bercher; Subbarao Kambhampati; |
647 | Landmark Heuristics for Lifted Classical Planning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We design two methods for landmark extraction in the lifted setting. |
Julia Wichlacz; Daniel Höller; Jörg Hoffmann; |
648 | Competitive Analysis for Multi-Commodity Ski-Rental Problem Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: It is a novel extension of the classical ski-rental problem which deals with only one commodity. To address this problem, we propose a new online algorithm called the Multi-Object Break-Even (MOBE) algorithm and conduct competitive analysis. |
Binghan Wu; Wei Bao; Dong Yuan; Bing Zhou; |
649 | An Online Learning Approach Towards Far-sighted Emergency Relief Planning Under Intentional Attacks in Conflict Areas Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To achieve a far-sighted emergency relief planning under attacks, we design an online learning approach which is proven to obtain a near-optimal solution of the offline problem when those online reveled parameters are i.i.d. sampled from an unknown distribution. |
Haoyu Yang; Kaiming Xiao; Lihua Liu; Hongbin Huang; Weiming Zhang; |
650 | PG3: Policy-Guided Planning for Generalized Policy Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we study generalized policy search-based methods with a focus on the score function used to guide the search over policies. |
Ryan Yang; Tom Silver; Aidan Curtis; Tomas Lozano-Perez; Leslie Kaelbling; |
651 | A Native Qualitative Numeric Planning Solver Based on AND/OR Graph Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a simpler characterization of QNP solutions and a new approach to solve QNP problems based on directly searching for a solution, which is a closed and terminating subgraph that contains a goal node, in the AND/OR graphs induced by QNP problems. |
Hemeng Zeng; Yikun Liang; Yongmei Liu; |
652 | Dynamic Car Dispatching and Pricing: Revenue and Fairness for Ridesharing Platforms Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We focus on the dispatching-pricing problem to maximize the total revenue while keeping both drivers and riders satisfied. |
Zishuo Zhao; Xi Chen; Xuefeng Zhang; Yuan Zhou; |
653 | Multi-robot Task Allocation in The Environment with Functional Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper studies the multi-robot task allocation in the environment with functional tasks. |
Fuhan Yan; Kai Di; |
654 | A Closed-Loop Perception, Decision-Making and Reasoning Mechanism for Human-Like Navigation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Abstract: Reliable navigation systems have a wide range of applications in robotics and autonomous driving. Current approaches employ an open-loop process that converts sensor inputs … |
Wenqi Zhang; Kai Zhao; Peng Li; Xiao Zhu; Yongliang Shen; Yanna Ma; Yingfeng Chen; Weiming Lu; |
655 | Robust Subset Selection By Greedy and Evolutionary Pareto Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper considers robust subset selection with monotone objective functions, relaxing the submodular property required by previous studies. |
Chao Bian; Yawen Zhou; Chao Qian; |
656 | Budgeted Sequence Submodular Maximization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Existing study on the problem only considers uniform costs over items, but non-uniform costs on items are more general. Taking this cue, we study the problem of budgeted sequence submodular maximization (BSSM), which introduces non-uniform costs of items into the sequence selection. |
Xuefeng Chen; Liang Feng; Xin Cao; Yifeng Zeng; Yaqing Hou; |
657 | Learning and Exploiting Progress States in Greedy Best-First Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce a novel approach that learns a description logic formula characterizing all progress states in a classical planning domain. |
Patrick Ferber; Liat Cohen; Jendrik Seipp; Thomas Keller; |
658 | Completeness and Diversity in Depth-First Proof-Number Search with Applications to Retrosynthesis Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We revisit Depth-First Proof-Number Search (DFPN), a well-known algorithm for solving two-player games. |
Christopher Franz; Georg Mogk; Thomas Mrziglod; Kevin Schewior; |
659 | Large Neighborhood Search with Decision Diagrams Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce a generic neighborhood exploration algorithm based on restricted decision diagrams (DD) constructed from the current best solution. |
Xavier Gillard; Pierre Schaus; |
660 | Efficient Budgeted Graph Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper reformulates BGS into Efficient Budgeted Graph Search (BGSe), showing how to implement the algorithm so that it behaves identically to A* when problems are well-behaved, and retains the best-case performance otherwise. |
Jasmeet Kaur; Nathan R. Sturtevant; |
661 | Generalisation of Alpha-Beta Search for AND-OR Graphs With Partially Ordered Values Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In particular, this setting generalises standard AND-OR graph evaluation and computation of optimal strategies in games with complete information. Under this setting, we propose a new algorithm which uses both alpha-beta pruning and cached values. |
Junkang Li; Bruno Zanuttini; Tristan Cazenave; Véronique Ventos; |
662 | Efficient Neural Neighborhood Search for Pickup and Delivery Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We present an efficient Neural Neighborhood Search (N2S) approach for pickup and delivery problems (PDPs). |
Yining Ma; Jingwen Li; Zhiguang Cao; Wen Song; Hongliang Guo; Yuejiao Gong; Yeow Meng Chee; |
663 | Real-Time Heuristic Search with LTLf Goals Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we consider a version of RTHS in which temporally extended goals can be defined on the form of the path. |
Jaime Middleton; Rodrigo Toro Icarte; Jorge Baier; |
664 | Reinforcement Learning for Cross-Domain Hyper-Heuristics Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a new hyper-heuristic approach that uses reinforcement learning to automatically learn the selection of low-level heuristics across a wide range of problem domains. |
Florian Mischek; Nysret Musliu; |
665 | Runtime Analysis of Single- and Multi-Objective Evolutionary Algorithms for Chance Constrained Optimization Problems with Normally Distributed Random Variables Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Considering the simple single-objective (1+1)~EA, we show that imposing an additional uniform constraint already leads to local optima for very restricted scenarios and an exponential optimization time. We therefore introduce a multi-objective formulation of the problem which trades off the expected cost and its variance. |
Frank Neumann; Carsten Witt; |
666 | Efficient Algorithms for Monotone Non-Submodular Maximization with Partition Matroid Constraint Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we study the problem of monotone non-submodular maximization with partition matroid constraint. |
Lan N. Nguyen; My T. Thai; |
667 | Neural Network Pruning By Cooperative Coevolution Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a new filter pruning algorithm CCEP by cooperative coevolution, which prunes the filters in each layer by EAs separately. |
Haopu Shang; Jia-Liang Wu; Wenjing Hong; Chao Qian; |
668 | HEA-D: A Hybrid Evolutionary Algorithm for Diversified Top-k Weight Clique Search Problem Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we formulate DTKWC search problem using mixed integer linear program constraints and propose an efficient hybrid evolutionary algorithm (HEA-D) that combines a clique-based crossover operator and an effective simulated annealing-based local optimization procedure to find high-quality local optima. |
Jun Wu; Chu-Min Li; Yupeng Zhou; Minghao Yin; Xin Xu; Dangdang Niu; |
669 | A Weighting-Based Tabu Search Algorithm for The P-Next Center Problem Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a weighting-based tabu search algorithm called WTS for solving pNCP. |
Qingyun Zhang; Zhouxing Su; Zhipeng Lü; Lingxiao Yang; |
670 | Summary Markov Models for Event Sequences Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Datasets involving sequences of different types of events without meaningful time stamps are prevalent in many applications, for instance when extracted from textual corpora. We propose a family of models for such event sequences — summary Markov models — where the probability of observing an event type depends only on a summary of historical occurrences of its influencing set of event types. |
Debarun Bhattacharjya; Saurabh Sihag; Oktie Hassanzadeh; Liza Bialik; |
671 | Ancestral Instrument Method for Causal Inference Without Complete Knowledge Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, by leveraging maximal ancestral graphs (MAGs) for causal inference with latent variables, we study the graphical properties of ancestral IVs, a type of conditional IVs using MAGs, and develop the theory to support data-driven discovery of the conditioning set for a given ancestral IV in data under the pretreatment variable assumption. |
Debo Cheng; Jiuyong Li; Lin Liu; Jiji Zhang; Thuc Duy Le; Jixue Liu; |
672 | Empirical Bayesian Approaches for Robust Constraint-based Causal Discovery Under Insufficient Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We apply proposed independence tests to constraint-based causal discovery methods and evaluate the performance on benchmark datasets with insufficient samples. |
Zijun Cui; Naiyu Yin; Yuru Wang; Qiang Ji; |
673 | Hidden 1-Counter Markov Models and How to Learn Them Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce hidden 1-counter Markov models (H1MMs) as an attractive sweet spot between standard hidden Markov models (HMMs) and probabilistic context-free grammars (PCFGs). |
Mehmet Kurucan; Mete Özbaltan; Sven Schewe; Dominik Wojtczak; |
674 | Exchangeability-Aware Sum-Product Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: The contribution of this paper is a novel probabilistic model which we call Exchangeability-Aware Sum-Product Networks (XSPNs). |
Stefan Lüdtke; Christian Bartelt; Heiner Stuckenschmidt; |
675 | Learning Cluster Causal Diagrams: An Information-Theoretic Approach Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a new scoring function, the Clustering Information Criterion (CIC), based on information-theoretic measures that represent various complex interactions among variables. |
Xueyan Niu; Xiaoyun Li; Ping Li; |
676 | Linear Combinatorial Semi-Bandit with Causally Related Rewards Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The objective is to maximize the long-term average payoff, which is a linear function of the base arms’ rewards and depends strongly on the network topology. To achieve this objective, we propose a policy that determines the causal relations by learning the network’s topology and simultaneously exploits this knowledge to optimize the decision-making process. |
Behzad Nourani-Koliji; Saeed Ghoorchian; Setareh Maghsudi; |
677 | Robustness Guarantees for Credal Bayesian Networks Via Constraint Relaxation Over Probabilistic Circuits Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work we develop a method to quantify the robustness of decision functions with respect to credal Bayesian networks, formal parametric models of the environment where uncertainty is expressed through credal sets on the parameters. |
Hjalmar Wijk; Benjie Wang; Marta Kwiatkowska; |
678 | On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, to raise the awareness of the research community on robust uncertainty estimation, we show that state-of-the-art uncertainty estimation algorithms could fail catastrophically under our proposed adversarial attack despite their impressive performance on uncertainty estimation. |
Huimin Zeng; Zhenrui Yue; Yang Zhang; Ziyi Kou; Lanyu Shang; Dong Wang; |
679 | DPVI: A Dynamic-Weight Particle-Based Variational Inference Framework Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose to dynamically adjust particles’ weights according to a Fisher-Rao reaction flow. |
Chao Zhang; Zhijian Li; Xin Du; Hui Qian; |
680 | Deep Interactive Surface Creation from 3D Sketch Strokes Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a deep neural framework that allows users to create surfaces from a stream of sparse 3D sketch strokes. |
Sukanya Bhattacharjee; Parag Chaudhuri; |
681 | Tradformer: A Transformer Model of Traditional Music Transcriptions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We explore the transformer neural network architecture for modeling music, specifically Irish and Swedish traditional dance music. |
Luca Casini; Bob L. T. Sturm; |
682 | Sound2Synth: Interpreting Sound Via FM Synthesizer Parameters Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: The problem of estimating a set of parameters configuration that best restore a sound timbre is an important yet complicated problem, i.e.: the synthesizer parameters estimation problem. We proposed a multi-modal deep-learning-based pipeline Sound2Synth, together with a network structure Prime-Dilated Convolution (PDC) specially designed to solve this problem. |
Zui Chen; Yansen Jing; Shengcheng Yuan; Yifei Xu; Jian Wu; Hang Zhao; |
683 | Towards Creativity Characterization of Generative Models Via Group-Based Subset Scanning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Thus, incorporating research on human creativity into generative deep learning techniques presents an opportunity to make their outputs more compelling and human-like. |
Celia Cintas; Payel Das; Brian Quanz; Girmaw Abebe Tadesse; Skyler Speakman; Pin-Yu Chen; |
684 | Art Creation with Multi-Conditional StyleGANs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we introduce a multi-conditional Generative Adversarial Network (GAN) approach trained on large amounts of human paintings to synthesize realistic-looking paintings that emulate human art. |
Konstantin Dobler; Florian Hübscher; Jan Westphal; Alejandro Sierra-Múnera; Gerard de Melo; Ralf Krestel; |
685 | Threshold Designer Adaptation: Improved Adaptation for Designers in Co-creative Systems Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we present threshold designer adaptation: a novel method for adapting a creative ML model to an individual designer. |
Emily Halina; Matthew Guzdial; |
686 | Automated Sifting of Stories from Simulated Storyworlds Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The goal of this work is to reduce the authoring burden for creating sifting queries. |
Wilkins Leong; Julie Porteous; John Thangarajah; |
687 | Universal Video Style Transfer Via Crystallization, Separation, and Blending Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, how to maintain the temporal consistency of videos while achieving high-quality arbitrary style transfer is still a hard nut to crack. To resolve this dilemma, in this paper, we propose the CSBNet which involves three key modules: 1) the Crystallization (Cr) Module that generates several orthogonal crystal nuclei, representing hierarchical stability-aware content and style components, from raw VGG features; 2) the Separation (Sp) Module that separates these crystal nuclei to generate the stability-enhanced content and style features; 3) the Blending (Bd) Module to cross-blend these stability-enhanced content and style features, producing more stable and higher-quality stylized videos. |
Haofei Lu; Zhizhong Wang; |
688 | StyleCLIPDraw: Coupling Content and Style in Text-to-Drawing Translation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We present an approach for generating styled drawings for a given text description where a user can specify a desired drawing style using a sample image. |
Peter Schaldenbrand; Zhixuan Liu; Jean Oh; |
689 | Dataset Augmentation in Papyrology with Generative Models: A Study of Synthetic Ancient Greek Character Images Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present findings from a study that assess the efficacy of using synthetically generated character instances to augment an existing dataset of ancient Greek character images for use in machine learning models. |
Matthew I. Swindall; Timothy Player; Ben Keener; Alex C. Williams; James H. Brusuelas; Federica Nicolardi; Marzia D’Angelo; Claudio Vergara; Michael McOsker; John F. Wallin; |
690 | DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, as another widespread research interest, the diversity of patch-based methods remains challenging due to the stereotyped style swapping process based on nearest patch matching. To resolve this dilemma, in this paper, we dive into the crux of existing patch-based methods and propose a universal and efficient module, termed DivSwapper, for diversified patch-based arbitrary style transfer. |
Zhizhong Wang; Lei Zhao; Haibo Chen; Zhiwen Zuo; Ailin Li; Wei Xing; Dongming Lu; |
691 | Music-to-Dance Generation with Optimal Transport Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a Music-to-Dance with Optimal Transport Network (MDOT-Net) for learning to generate 3D dance choreographies from music. |
Shuang Wu; Shijian Lu; Li Cheng; |
692 | Composition-aware Graphic Layout GAN for Visual-Textual Presentation Designs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we study the graphic layout generation problem of producing high-quality visual-textual presentation designs for given images. |
Min Zhou; Chenchen Xu; Ye Ma; Tiezheng Ge; Yuning Jiang; Weiwei Xu; |
693 | Style Fader Generative Adversarial Networks for Style Degree Controllable Artistic Style Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address the issue, in this paper, we propose a novel method that for the first time allows adjusting the style degree for existing GAN-based artistic style transfer frameworks in real time after training. |
Zhiwen Zuo; Lei Zhao; Shuobin Lian; Haibo Chen; Zhizhong Wang; Ailin Li; Wei Xing; Dongming Lu; |
694 | Captioning Bosch: A Twitter Bot Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: As the model was only trained on realistic, photographic images, curious interpretations of the otherworldly details can be observed. |
Cornelia Ferner; |
695 | High-Resolution and Arbitrary-Sized Chinese Landscape Painting Creation Based on Generative Adversarial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper outlines an automated creation system for Chinese landscape paintings based on generative adversarial networks. |
Peixiang Luo; Jinchao Zhang; Jie Zhou; |
696 | Learning to Generate Poetic Chinese Landscape Painting with Calligraphy Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a novel system (denoted as Polaca) to generate poetic Chinese landscape painting with calligraphy. |
Shaozu Yuan; Aijun Dai; Zhiling Yan; Ruixue Liu; Meng Chen; Baoyang Chen; Zhijie Qiu; Xiaodong He; |
697 | Learning Pollution Maps from Mobile Phone Images Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a low-cost, end-to-end system for learning pollution maps using images captured through a mobile phone. |
Ankit Bhardwaj; Shiva Iyer; Yash Jalan; Lakshminarayanan Subramanian; |
698 | Deciphering Environmental Air Pollution with Large Scale City Data Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, the lack of large scale data involving the major artificial and natural factors has hindered the research on the causes and relations governing the variability of the different air pollutants. Through this work, we introduce a large scale city-wise dataset for exploring the relationships among these agents over a long period of time. |
Mayukh Bhattacharyya; Sayan Nag; Udita Ghosh; |
699 | Chronic Disease Management with Personalized Lab Test Response Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Accurate prediction of lab test response is a challenge because these patients typically have co-morbidities and their treatments might influence the target lab test response. To address this, we model the complex interactions among different medications, diseases, lab test response, and fine-grained dosage information to learn a strong patient representation. |
Suman Bhoi; Mong Li Lee; Wynne Hsu; Hao Sen Andrew Fang; Ngiap Chuan Tan; |
700 | AggPose: Deep Aggregation Vision Transformer for Infant Pose Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, most of the newest AI approaches for human pose estimation methods focus on adults, lacking publicly benchmark for infant pose estimation. In this paper, we fill this gap by proposing infant pose dataset and Deep Aggregation Vision Transformer for human pose estimation, which introduces a fast trained full transformer framework without using convolution operations to extract features in the early stages. |
Xu Cao; Xiaoye Li; Liya Ma; Yi Huang; Xuan Feng; Zening Chen; Hongwu Zeng; Jianguo Cao; |
701 | Forecasting Patient Outcomes in Kidney Exchange Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose the first decision-support tool for kidney exchange that takes as input the biological features of a patient-donor pair, and returns (i) the probability of being matched prior to expiry, and (conditioned on a match outcome), (ii) the waiting time for and (iii) the organ quality of the matched transplant. |
Naveen Durvasula; Aravind Srinivasan; John Dickerson; |
702 | A Murder and Protests, The Capitol Riot, and The Chauvin Trial: Estimating Disparate News Media Stance Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we analyze the responses of three major US cable news networks to three seminal policing events in the US spanning a thirteen month period–the murder of George Floyd by police officer Derek Chauvin, the Capitol riot, Chauvin’s conviction, and his sentencing. |
Sujan Dutta; Beibei Li; Daniel S. Nagin; Ashiqur R. KhudaBukhsh; |
703 | Monitoring Vegetation From Space at Extremely Fine Resolutions Via Coarsely-Supervised Smooth U-Net Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We also have additional fine-resolution input features, but the relationship between these features and SIF is unknown. To address this, we propose Coarsely-Supervised Smooth U-Net (CS-SUNet), a novel method for this coarse supervision setting. |
Joshua Fan; Di Chen; Jiaming Wen; Ying Sun; Carla Gomes; |
704 | Am I No Good? Towards Detecting Perceived Burdensomeness and Thwarted Belongingness from Suicide Notes Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present an end-to-end multitask system to address a novel task of detection of two interpersonal risk factors of suicide, Perceived Burdensomeness (PB) and Thwarted Belongingness (TB) from suicide notes. |
Soumitra Ghosh; Asif Ekbal; Pushpak Bhattacharyya; |
705 | AI Facilitated Isolations? The Impact of Recommendation-based Influence Diffusion in Human Society Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The increasing personalization raises the hypotheses of the "filter bubble" and "echo chamber" effects. To investigate these hypotheses, in this paper, we inspect the impact of recommendation algorithms on forming two types of ideological isolation, i.e., the individual isolation and the topological isolation, in terms of the filter bubble and echo chamber effects, respectively. |
Yuxuan Hu; Shiqing Wu; Chenting Jiang; Weihua Li; Quan Bai; Erin Roehrer; |
706 | Crowd, Expert & AI: A Human-AI Interactive Approach Towards Natural Language Explanation Based COVID-19 Misinformation Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we study an explainable COVID-19 misinformation detection problem where the goal is to accurately identify COVID-19 misleading posts on social media and explain the posts with natural language explanations (NLEs). |
Ziyi Kou; Lanyu Shang; Yang Zhang; Zhenrui Yue; Huimin Zeng; Dong Wang; |
707 | Towards The Quantitative Interpretability Analysis of Citizens Happiness Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Recently, deep learning shows promising prediction accuracy while addressing challenges in interpretability. To this end, we introduce Shapley value that is inherent in solid theory for factor contribution interpretability to work with deep learning models by taking into account interactions between multiple factors. |
Lin Li; Xiaohua Wu; Miao Kong; Dong Zhou; Xiaohui Tao; |
708 | S2SNet: A Pretrained Neural Network for Superconductivity Discovery Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Hence a new dataset, S2S, containing both crystal structures and superconducting critical temperature, is built upon SuperCon and Material Project. Based on this new dataset, we propose a novel model, S2SNet, which utilizes the attention mechanism for superconductivity prediction. |
Ke Liu; Kaifan Yang; Jiahong Zhang; Renjun Xu; |
709 | Creating Dynamic Checklists Via Bayesian Case-Based Reasoning: Towards Decent Working Conditions for All Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In contrast, we propose a new method called Context-aware Bayesian Case-Based Reasoning (CBCBR) that creates dynamic checklists. |
Eirik Lund Flogard; Ole Jakob Mengshoel; Kerstin Bach; |
710 | A Reliability-aware Distributed Framework to Schedule Residential Charging of Electric Vehicles Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we address the problem of scheduling residential EV charging for multiple consumers while maintaining network reliability. |
Rounak Meyur; Swapna Thorve; Madhav Marathe; Anil Vullikanti; Samarth Swarup; Henning Mortveit; |
711 | Gigs with Guarantees: Achieving Fair Wage for Food Delivery Workers Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose Work4Food, which provides income guarantees to delivery agents, while minimizing platform costs and ensuring customer satisfaction. |
Ashish Nair; Rahul Yadav; Anjali Gupta; Abhijnan Chakraborty; Sayan Ranu; Amitabha Bagchi; |
712 | ADVISER: AI-Driven Vaccination Intervention Optimiser for Increasing Vaccine Uptake in Nigeria Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a heuristic approach that enables us to solve the problem for real-world use-cases. |
Vineet Nair; Kritika Prakash; Michael Wilbur; Aparna Taneja; Corrine Namblard; Oyindamola Adeyemo; Abhishek Dubey; Abiodun Adereni; Milind Tambe; Ayan Mukhopadhyay; |
713 | Ownership Concentration and Wealth Inequality in Russia Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Here we propose a robust and scalable network-based algorithm to reveal hidden ultimate owners in public ownership data. |
Kirill Polovnikov; Nikita Pospelov; Dmitriy Skougarevskiy; |
714 | DiRe Committee : Diversity and Representation Constraints in Multiwinner Elections Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Hence, we develop a model, DiRe Committee Winner Determination (DRCWD), which delineates candidate and voter attributes to select a committee by specifying diversity and representation constraints and a voting rule. |
Kunal Relia; |
715 | AgriBERT: Knowledge-Infused Agricultural Language Models for Matching Food and Nutrition Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We evaluate our trained language model, called AgriBERT, on the task of semantic matching, i.e., establishing mapping between food descriptions and nutrition data, which is a long-standing challenge in the agricultural domain. In particular, we formulate the task as an answer selection problem, fine-tune the trained language model with the help of an external source of knowledge (e.g., FoodOn ontology), and establish a baseline for this task. |
Saed Rezayi; Zhengliang Liu; Zihao Wu; Chandra Dhakal; Bao Ge; Chen Zhen; Tianming Liu; Sheng Li; |
716 | CounterGeDi: A Controllable Approach to Generate Polite, Detoxified and Emotional Counterspeech Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose CounterGeDi – an ensemble of generative discriminators (GeDi) to guide the generation of a DialoGPT model toward more polite, detoxified, and emotionally laden counterspeech. |
Punyajoy Saha; Kanishk Singh; Adarsh Kumar; Binny Mathew; Animesh Mukherjee; |
717 | Scalable and Memory-Efficient Algorithms for Controlling Networked Epidemic Processes Using Multiplicative Weights Update Method Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In particular, the mathematical-programming based approaches need to solve the Linear Program (LP) relaxation of the problem using an LP solver, which restricts the scalability of this approach. In this work, we overcome this restriction by designing an algorithm that adapts the multiplicative weights update (MWU) framework, along with the sample average approximation (SAA) technique, to approximately solve the linear program (LP) relaxation for the problem. |
Prathyush Sambaturu; Marco Minutoli; Mahantesh Halappanavar; Ananth Kalyanaraman; Anil Vullikanti; |
718 | Revealing The Excitation Causality Between Climate and Political Violence Via A Neural Forward-Intensity Poisson Process Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Here, we aim to overcome the aforementioned causal modeling challenges by proposing a neural forward-intensity Poisson process (NFIPP) model. |
Schyler C. Sun; Bailu Jin; Zhuangkun Wei; Weisi Guo; |
719 | Forecasting The Number of Tenants At-Risk of Formal Eviction: A Machine Learning Approach to Inform Public Policy Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To help enhance the existing eviction prevention/diversion programs, in this work, we propose a multi-view deep neural network model, named as MARTIAN, that forecasts the number of tenants at-risk of getting formally evicted (at the census tract level) n months into the future. |
Maryam Tabar; Wooyong Jung; Amulya Yadav; Owen Wilson Chavez; Ashley Flores; Dongwon Lee; |
720 | Dynamic Structure Learning Through Graph Neural Network for Forecasting Soil Moisture in Precision Agriculture Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose a novel graph neural network based solution that learns temporal graph structures and forecast soil moisture in an end-to-end framework. |
Anoushka Vyas; Sambaran Bandyopadhyay; |
721 | Quantifying Health Inequalities Induced By Data and AI Models Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper proposes a generic allocation-deterioration framework for detecting and quantifying AI induced inequality. |
Honghan Wu; Aneeta Sylolypavan; Minhong Wang; Sarah Wild; |
722 | Sequential Vaccine Allocation with Delayed Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work we consider the problem of how to best allocate a limited supply of vaccines in the aftermath of an infectious disease outbreak by viewing the problem as a sequential game between a learner and an environment (specifically, a bandit problem). |
Yichen Xiao; Han-Ching Ou; Haipeng Chen; Van Thieu Nguyen; Long Tran-Thanh; |
723 | Ranked Prioritization of Groups in Combinatorial Bandit Allocation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: When some species are more vulnerable, we ought to offer more protection to these animals; unfortunately, existing combinatorial bandit approaches do not offer a way to prioritize important species. To bridge this gap, (1) We propose a novel combinatorial bandit objective that trades off between reward maximization and also accounts for prioritization over species, which we call ranked prioritization. |
Lily Xu; Arpita Biswas; Fei Fang; Milind Tambe; |
724 | Conversational Inequality Through The Lens of Political Interruption Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a novel dataset of dialogues containing interruption with an aim to conduct a large-scale analysis of interruption patterns of people from diverse backgrounds in terms of gender, race/ethnicity, occupation, and political orientation. |
Clay H. Yoo; Jiachen Wang; Yuxi Luo; Kunal Khadilkar; Ashiqur R. KhudaBukhsh; |
725 | Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: For ERD, we propose an online algorithm based on an evolving queue of risky posts that can significantly reduce the number of model inferences to boost efficiency. |
Zhiling Zhang; Siyuan Chen; Mengyue Wu; Kenny Q. Zhu; |
726 | A Norm Optimisation Approach to SDGs: Tackling Poverty By Acting on Discrimination Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Through the formulation and development of an agent-based social simulation, this study aims to analyse the role of norms implementing equal opportunity and social solidarity principles as enhancers or mitigators of aporophobia, as well as the threshold of aporophobia that would facilitate the success of poverty-reduction policies. |
Georgina Curto; Nieves Montes; Carles Sierra; Nardine Osman; Flavio Comim; |
727 | Interactive Concept-map Based Summaries for SEND Children Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Traditional approaches to learning propose education paths performed with speech therapists. |
Martina Galletti; Michael Anslow; Francesca Bianchi; Manuela Calanca; Donatella Tomaiuoli; Remi Van Trijp; Diletta Vedovelli; Eleonora Pasqua; |
728 | Argo: Towards Small Vessel Detection for Humanitarian Purposes Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present Argo: a semi-automatically created vessel classification dataset focused on small boats, with the aim to enable NGOs and the public to detect refugee boats in satellite imagery. |
Elisabeth Moser; Selina Meyer; Maximilian Schmidhuber; Daniel Ketterer; Matthias Eberhardt; |
729 | Climate Bot: A Machine Reading Comprehension System for Climate Change Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This demo paper presents Climate Bot – a machine reading comprehension system for question answering over documents about climate change. |
Md Rashad Al Hasan Rony; Ying Zuo; Liubov Kovriguina; Roman Teucher; Jens Lehmann; |
730 | On The Expressivity of Markov Reward (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We here set out to understand the expressivity of Markov reward as a way to capture tasks that we would want an agent to perform. |
David Abel; Will Dabney; Anna Harutyunyan; Mark K. Ho; Michael L. Littman; Doina Precup; Satinder Singh; |
731 | Improving Inductive Link Prediction Using Hyper-Relational Facts (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we classify different inductive settings and study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by recent advancements in graph neural networks. |
Mehdi Ali; Max Berrendorf; Mikhail Galkin; Veronika Thost; Tengfei Ma; Volker Tresp; Jens Lehmann; |
732 | Utilizing Treewidth for Quantitative Reasoning on Epistemic Logic Programs (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Extending the popular Answer Set Programming (ASP) paradigm by introspective reasoning capacities has received increasing interest within the last years. Particular attention is … |
Viktor Besin; Markus Hecher; Stefan Woltran; |
733 | Capturing Homomorphism-Closed Decidable Queries with Existential Rules (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Existential rules are a very popular ontology-mediated query language for which the chase represents a generic computational approach for query answering. |
Camille Bourgaux; David Carral; Markus Krötzsch; Sebastian Rudolph; Michaël Thomazo; |
734 | Deep Cooperation of CDCL and Local Search for SAT (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We use our techniques to improve three typical CDCL solvers (glucose, MapleLCMDistChronoBT and Kissat). |
Shaowei Cai; Xindi Zhang; |
735 | Scalable Anytime Planning for Multi-Agent MDPs (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a scalable planning algorithm for multi-agent sequential decision problems that require dynamic collaboration. |
Shushman Choudhury; Jayesh K. Gupta; Mykel J. Kochenderfer; |
736 | Measuring Data Leakage in Machine-Learning Models with Fisher Information (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Consequently, when the training data contains sensitive attributes, assessing the amount of information leakage is paramount. We propose a method to quantify this leakage using the Fisher information of the model about the data. |
Awni Hannun; Chuan Guo; Laurens van der Maaten; |
737 | Allocating Opportunities in A Dynamic Model of Intergenerational Mobility (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Opportunities such as higher education can promote intergenerational mobility, leading individuals to achieve levels of socioeconomic status above that of their parents. In this work, which is an extended abstract of a longer paper in the proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, we develop a dynamic model for allocating such opportunities in a society that exhibits bottlenecks in mobility; the problem of optimal allocation reflects a trade-off between the benefits conferred by the opportunities in the current generation and the potential to elevate the socioeconomic status of recipients, shaping the composition of future generations in ways that can benefit further from the opportunities. |
Hoda Heidari; Jon Kleinberg; |
738 | Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families Via Mirror Descent (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we show that for the common setting of exponential family distributions, viewing EM as a mirror descent algorithm leads to convergence rates in Kullback-Leibler (KL) divergence and how the KL divergence is related to first-order stationarity via Bregman divergences. |
Frederik Kunstner; Raunak Kumar; Mark Schmidt; |
739 | Combining Clause Learning and Branch and Bound for MaxSAT (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Branch and Bound (BnB) has been successfully used to solve many combinatorial optimization problems. However, BnB MaxSAT solvers perform poorly when solving real-world and … |
Chu-Min Li; Zhenxing Xu; Jordi Coll; Felip Manyà; Djamal Habet; Kun He; |
740 | Open Data Science to Fight COVID-19: Winning The 500k XPRIZE Pandemic Response Challenge (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We describe the deep learning-based COVID-19 cases predictor and the Pareto-optimal Non-Pharmaceutical Intervention (NPI) prescriptor developed by the winning team of the 500k XPRIZE Pandemic Response Challenge. |
Miguel Angel Lozano; Òscar Garibo-i-Orts; Eloy Piñol; Miguel Rebollo; Kristina Polotskaya; Miguel Ángel García-March; J. Alberto Conejero; Francisco Escolano; Nuria Oliver; |
741 | Complex Query Answering with Neural Link Predictors (Extended Abstract)* Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a framework for efficiently answering complex queries on in- complete Knowledge Graphs. |
Pasquale Minervini; Erik Arakelyan; Daniel Daza; Michael Cochez; |
742 | Detect, Understand, Act: A Neuro-Symbolic Hierarchical Reinforcement Learning Framework (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce Detect, Understand, Act (DUA), a neuro-symbolic reinforcement learning framework. |
Ludovico Mitchener; David Tuckey; Matthew Crosby; Alessandra Russo; |
743 | Computationally Efficient Optimization of Plackett-Luce Ranking Models for Relevance and Fairness (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we introduce a novel algorithm: PL-Rank, that estimates the gradient of a PL ranking model through sampling. |
Harrie Oosterhuis; |
744 | Logic Rules Meet Deep Learning: A Novel Approach for Ship Type Classification (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a novel ship type classification model that combines vessel transmitted data from the Automatic Identification System, with vessel imagery. |
Manolis Pitsikalis; Thanh-Toan Do; Alexei Lisitsa; Shan Luo; |
745 | Asymmetric Hybrids: Dialogues for Computational Concept Combination (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We focus in particular on the case where a Head concept has superior ‘asymmetric’ control over steering the resulting combination (or hybridisation) with a Modifier concept. Specifically, we propose a dialogical model of the cognitive and logical mechanics of this asymmetric form of hybridisation. |
Guendalina Righetti; Daniele Porello; Nicolas Troquard; Oliver Kutz; Maria Hedblom; Pietro Galliani; |
746 | Computing Programs for Generalized Planning As Heuristic Search (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper adapts the planning as heuristic search paradigm to the particularities of GP, and presents the first native heuristic search approach to GP. |
Javier Segovia-Aguas; Sergio Jiménez Celorrio; Anders Jonsson; |
747 | Towards Facilitating Empathic Conversations in Online Mental Health Support: A Reinforcement Learning Approach (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we work towards improving empathy in online mental health support conversations. |
Ashish Sharma; Inna W. Lin; Adam S. Miner; Dave C. Atkins; Tim Althoff; |
748 | ProtoAI: Model-Informed Prototyping for AI-Powered Interfaces (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose Model-Informed Prototyping (MIP), a workflow for AIX design that combines model exploration with UI prototyping tasks. |
Hariharan Subramonyam; Colleen Seifert; Eytan Adar; |
749 | Black-box Audit of YouTube’s Video Recommendation: Investigation of Misinformation Filter Bubble Dynamics (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we describe a black-box sockpuppeting audit which we carried out to investigate the creation and bursting dynamics of misinformation filter bubbles on YouTube. |
Matus Tomlein; Branislav Pecher; Jakub Simko; Ivan Srba; Robert Moro; Elena Stefancova; Michal Kompan; Andrea Hrckova; Juraj Podrouzek; Maria Bielikova; |
750 | Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce a method called Persistent Evolution Strategies (PES), which divides the computation graph into a series of truncated unrolls, and performs an evolution strategies-based update step after each unroll. |
Paul Vicol; Luke Metz; Jascha Sohl-Dickstein; |
751 | The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a novel lower bound with a matching upper bound that establishes an optimal algorithm. |
Blake Woodworth; Brian Bullins; Ohad Shamir; Nathan Srebro; |
752 | Statistically-Guided Deep Network Transformation to Harness Heterogeneity in Space (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a statistically-guided framework to adaptively partition data in space during training using distribution-driven optimization and transform a deep learning model (of user’s choice) into a heterogeneity-aware architecture. |
Yiqun Xie; Erhu He; Xiaowei Jia; Han Bao; Xun Zhou; Rahul Ghosh; Praveen Ravirathinam; |
753 | Including Signed Languages in Natural Language Processing (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Signed languages are the primary means of communication for many deaf and hard of hearing individuals. Since signed languages exhibit all the fundamental linguistic properties of … |
Kayo Yin; Malihe Alikhani; |
754 | Learning Discrete Representations Via Constrained Clustering for Effective and Efficient Dense Retrieval (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor search (NNS) in vector space. Therefore, we present RepCONC, a novel retrieval model that learns discrete Representations via CONstrained Clustering. |
Jingtao Zhan; Jiaxin Mao; Yiqun Liu; Jiafeng Guo; Min Zhang; Shaoping Ma; |
755 | Rx-refill Graph Neural Network to Reduce Drug Overprescribing Risks (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel model RxNet, which builds 1) a dynamic heterogeneous graph to model Rx refills that are essentially prescribing and dispensing (P&D) relationships among various patients, 2) an RxLSTM network to explore the dynamic Rx-refill behavior and medical condition variation of patients, and 3) a dosing-adaptive network to extract and recalibrate dosing patterns and obtain the refined patient representations which are finally utilized for overprescribing detection. |
Jianfei Zhang; Ai-Te Kuo; Jianan Zhao; Qianlong Wen; Erin Winstanley; Chuxu Zhang; Yanfang Ye; |
756 | Fair Division of Indivisible Goods: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Recently, there has been a surge of papers studying computational questions regarding various different notions of fairness for the indivisible case, like maximin share fairness (MMS) and envy-freeness up to any good (EFX). |
Georgios Amanatidis; Georgios Birmpas; Aris Filos-Ratsikas; Alexandros A. Voudouris; |
757 | Text Transformations in Contrastive Self-Supervised Learning: A Review Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this review paper, we formalize the contrastive learning framework, emphasize the considerations that need to be addressed in the data transformation step, and review the state-of-the-art methods and evaluations for contrastive representation learning in NLP. |
Amrita Bhattacharjee; Mansooreh Karami; Huan Liu; |
758 | A Survey on Word Meta-Embedding Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To the best of our knowledge, there exist no prior systematic survey on ME learning and this paper attempts to fill this need. We classify ME learning methods according to multiple factors such as whether they (a) operate on static or contextualised embeddings, (b) trained in an unsupervised manner or (c) fine-tuned for a particular task/domain. |
Danushka Bollegala; James O’ Neill; |
759 | Image-text Retrieval: A Survey on Recent Research and Development Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper presents a comprehensive and up-to-date survey on the ITR approaches from four perspectives. |
Min Cao; Shiping Li; Juntao Li; Liqiang Nie; Min Zhang; |
760 | Evidential Reasoning and Learning: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we focus on techniques that take the name of evidential reasoning and learning from the process of Bayesian update of given hypotheses based on additional evidence. |
Federico Cerutti; Lance M. Kaplan; Murat Şensoy; |
761 | Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This survey aims to provide a comprehensive review of model designs, pre-training objectives, and downstream tasks for table pre-training, and we further share our thoughts on existing challenges and future opportunities. |
Haoyu Dong; Zhoujun Cheng; Xinyi He; Mengyu Zhou; Anda Zhou; Fan Zhou; Ao Liu; Shi Han; Dongmei Zhang; |
762 | A Survey of Vision-Language Pre-Trained Models Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we review the recent progress in Vision-Language Pre-Trained Models (VL-PTMs). |
Yifan Du; Zikang Liu; Junyi Li; Wayne Xin Zhao; |
763 | A Survey on Machine Learning Approaches for Modelling Intuitive Physics Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Especially at the intersection of intuitive physics and artificial intelligence, there is a need to make sense of the diverse range of ideas and approaches. Therefore, this paper presents a comprehensive survey of recent advances and techniques in intuitive physics-inspired deep learning approaches for physical reasoning. |
Jiafei Duan; Arijit Dasgupta; Jason Fischer; Cheston Tan; |
764 | A Survey on Dialogue Summarization: Recent Advances and New Frontiers Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, there still remains a lack of a comprehensive survey for this task. To this end, we take the first step and present a thorough review of this research field carefully and widely. |
Xiachong Feng; Xiaocheng Feng; Bing Qin; |
765 | Legal Judgment Prediction: A Survey of The State of The Art Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present an overview of the major milestones made in LJP research covering multiple jurisdictions and multiple languages, and conclude with promising future research directions. |
Yi Feng; Chuanyi Li; Vincent Ng; |
766 | Differential Privacy and Fairness in Decisions and Learning Tasks: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The survey reviews the conditions under which privacy and fairness may be aligned or contrasting goals, analyzes how and why DP exacerbates bias and unfairness in decision problems and learning tasks, and reviews the available solutions to mitigate the fairness issues arising in DP systems. |
Ferdinando Fioretto; Cuong Tran; Pascal Van Hentenryck; Keyu Zhu; |
767 | Deep Learning with Logical Constraints Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In recent years, there has been an increasing interest in exploiting logically specified background knowledge in order to obtain neural models (i) with a better performance, (ii) able to learn from less data, and/or (iii) guaranteed to be compliant with the background knowledge itself, e.g., for safety-critical applications. In this survey, we retrace such works and categorize them based on (i) the logical language that they use to express the background knowledge and (ii) the goals that they achieve. |
Eleonora Giunchiglia; Mihaela Catalina Stoian; Thomas Lukasiewicz; |
768 | Who Says What to Whom: A Survey of Multi-Party Conversations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a comprehensive survey of recent advances in text-based MPCs. |
Jia-Chen Gu; Chongyang Tao; Zhen-Hua Ling; |
769 | Survey on Efficient Training of Large Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We analyze techniques that save memory and make good use of computation and communication resources on architectures with a single or several GPUs. |
Julia Gusak; Daria Cherniuk; Alena Shilova; Alexandr Katrutsa; Daniel Bershatsky; Xunyi Zhao; Lionel Eyraud-Dubois; Oleh Shliazhko; Denis Dimitrov; Ivan Oseledets; Olivier Beaumont; |
770 | Goal-Conditioned Reinforcement Learning: Problems and Solutions Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this survey, we provide a comprehensive overview of the challenges and algorithms for GCRL. |
Minghuan Liu; Menghui Zhu; Weinan Zhang; |
771 | Neural Re-ranking in Multi-stage Recommender Systems: A Review Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This review aims at integrating re-ranking algorithms into a broader picture, and paving ways for more comprehensive solutions for future research. |
Weiwen Liu; Yunjia Xi; Jiarui Qin; Fei Sun; Bo Chen; Weinan Zhang; Rui Zhang; Ruiming Tang; |
772 | Survey on Graph Neural Network Acceleration: An Algorithmic Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we provide a comprehensive survey on acceleration methods for GNNs from an algorithmic perspective. |
Xin Liu; Mingyu Yan; Lei Deng; Guoqi Li; Xiaochun Ye; Dongrui Fan; Shirui Pan; Yuan Xie; |
773 | Vision-and-Language Pretrained Models: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present an overview of the major advances achieved in VLPMs for producing joint representations of vision and language. |
Siqu Long; Feiqi Cao; Soyeon Caren Han; Haiqin Yang; |
774 | Predictive Coding: Towards A Future of Deep Learning Beyond Backpropagation? Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this survey, we review works that have contributed to this perspective and demonstrate the close connection between predictive coding and backpropagation in terms of generalization quality, as well as works that highlight the multiple advantages of using predictive coding models over backprop-trained neural networks. |
Beren Millidge; Tommaso Salvatori; Yuhang Song; Rafal Bogacz; Thomas Lukasiewicz; |
775 | Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Code Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In particular, the development and use of pre-trained models of source code has enabled state-of-the-art results to be achieved on a wide variety of SE tasks. This paper provides an overview of this rapidly advancing field of research and reflects on future research directions. |
Changan Niu; Chuanyi Li; Bin Luo; Vincent Ng; |
776 | Evaluation Methods for Representation Learning: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To understand the current applications of representation learning, we review evaluation methods of representation learning algorithms. |
Kento Nozawa; Issei Sato; |
777 | A Unified View of Relational Deep Learning for Drug Pair Scoring Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In recent years, numerous machine learning models which attempt to solve polypharmacy side effect identification, drug-drug interaction prediction, and combination therapy design tasks have been proposed. |
Benedek Rozemberczki; Stephen Bonner; Andriy Nikolov; Michaël Ughetto; Sebastian Nilsson; Eliseo Papa; |
778 | The Shapley Value in Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We examine the most crucial limitations of the Shapley value and point out directions for future research. |
Benedek Rozemberczki; Lauren Watson; Péter Bayer; Hao-Tsung Yang; Olivér Kiss; Sebastian Nilsson; Rik Sarkar; |
779 | A Survey of Machine Narrative Reading Comprehension Assessments Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Based on narrative theories, reading comprehension theories, as well as existing machine narrative reading comprehension tasks and datasets, we propose a typology that captures the main similarities and differences among assessment tasks; and discuss the implications of our typology for new task design and the challenges of narrative reading comprehension. |
Yisi Sang; Xiangyang Mou; Jing Li; Jeffrey Stanton; Mo Yu; |
780 | Abstraction for Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We review developments in AI and machine learning that could facilitate their adoption. |
Murray Shanahan; Melanie Mitchell; |
781 | Detecting and Understanding Harmful Memes: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We conclude by highlighting several challenges related to multimodal semiotics, technological constraints, and non-trivial social engagement, and we present several open-ended aspects such as delineating online harm and empirically examining related frameworks and assistive interventions, which we believe will motivate and drive future research. |
Shivam Sharma; Firoj Alam; Md. Shad Akhtar; Dimitar Dimitrov; Giovanni Da San Martino; Hamed Firooz; Alon Halevy; Fabrizio Silvestri; Preslav Nakov; Tanmoy Chakraborty; |
782 | Data Valuation in Machine Learning: "Ingredients", Strategies, and Open Challenges Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Data valuation is used in collaborative ML to determine a fair compensation for every data owner and in interpretable ML to identify the most responsible, noisy, or misleading training examples. This paper presents a comprehensive technical survey that provides a new formal study of data valuation in ML through its “ingredients” and the corresponding properties, grounds the discussion of common desiderata satisfied by existing data valuation strategies on our proposed ingredients, and identifies open research challenges for designing new ingredients, data valuation strategies, and cost reduction techniques. |
Rachael Hwee Ling Sim; Xinyi Xu; Bryan Kian Hsiang Low; |
783 | Problem Compilation for Multi-Agent Path Finding: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this survey, we summarize major compilation-based solvers for MAPF using CSP, SAT, and MILP formalisms. |
Pavel Surynek; |
784 | A Survey of Risk-Aware Multi-Armed Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This survey aims to consolidate and summarise the existing research on risk measures, specifically in the context of multi-armed bandits. |
Vincent Y. F. Tan; Prashanth L.A.; Krishna Jagannathan; |
785 | Vision-based Intention and Trajectory Prediction in Autonomous Vehicles: A Survey Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This survey targets intention and trajectory prediction in Autonomous Vehicles (AV), as AV companies compete to create dedicated prediction pipelines to avoid collisions. |
Izzeddin Teeti; Salman Khan; Ajmal Shahbaz; Andrew Bradley; Fabio Cuzzolin; |
786 | Recent Advances on Neural Network Pruning at Initialization Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Neural network pruning typically removes connections or neurons from a pretrained converged model; while a new pruning paradigm, pruning at initialization (PaI), attempts to prune a randomly initialized network. This paper offers the first survey concentrated on this emerging pruning fashion. |
Huan Wang; Can Qin; Yue Bai; Yulun Zhang; Yun Fu; |
787 | On The Opportunity of Causal Learning in Recommendation Systems: Foundation, Estimation, Prediction and Challenges Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Many causal-based prediction and debiasing studies rarely discuss the causal interpretation of various biases and the rationality of the corresponding causal assumptions. |
Peng Wu; Haoxuan Li; Yuhao Deng; Wenjie Hu; Quanyu Dai; Zhenhua Dong; Jie Sun; Rui Zhang; Xiao-Hua Zhou; |
788 | Recent Advances in Concept Drift Adaptation Methods for Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we first mathematically describe the categories of concept drift including abrupt drift, gradual drift, recurrent drift, incremental drift. |
Liheng Yuan; Heng Li; Beihao Xia; Cuiying Gao; Mingyue Liu; Wei Yuan; Xinge You; |
789 | Few-Shot Learning on Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: There have been many studies working on FSLG recently. In this paper, we comprehensively survey these work in the form of a series of methods and applications. |
Chuxu Zhang; Kaize Ding; Jundong Li; Xiangliang Zhang; Yanfang Ye; Nitesh V. Chawla; Huan Liu; |
790 | Recent Advances and New Frontiers in Spiking Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper reviews recent advances and discusses new frontiers in SNNs from five major research topics, including essential elements (i.e., spiking neuron models, encoding methods, and topology structures), neuromorphic datasets, optimization algorithms, software, and hardware frameworks. |
Duzhen Zhang; Tielin Zhang; Shuncheng Jia; Qingyu Wang; Bo Xu; |
791 | A Survey on Gradient Inversion: Attacks, Defenses and Future Directions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a comprehensive survey on GradInv, aiming to summarize the cutting-edge research and broaden the horizons for different domains. |
Rui Zhang; Song Guo; Junxiao Wang; Xin Xie; Dacheng Tao; |
792 | Towards Verifiable Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Currently, there is no comprehensive survey on the field of verifiable federated learning, which is interdisciplinary in nature and can be challenging for researchers to enter into. In this paper, we bridge this gap by reviewing works focusing on verifiable FL. |
Yanci Zhang; Han Yu; |
793 | A Survey on Neural Open Information Extraction: Current Status and Future Directions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this survey, we provide an extensive overview of the state-of-the-art neural OpenIE models, their key design decisions, strengths and weakness. |
Shaowen Zhou; Bowen Yu; Aixin Sun; Cheng Long; Jingyang Li; Jian Sun; |
794 | On The First-Order Rewritability of Ontology-Mediated Queries in Linear Temporal Logic (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We argue that linear temporal logic LTL in tandem with monadic first-order logic can be used as a ba- sic language for ontology-based access to tempo- ral data and obtain a classification of the resulting ontology-mediated queries according to the type of standard first-order queries they can be rewritten to. |
Alessandro Artale; Roman Kontchakov; Alisa Kovtunova; Vladislav Ryzhikov; Frank Wolter; Michael Zakharyaschev; |
795 | Bayesian Auctions with Efficient Queries (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work we consider, for the first time, the query complexityof Bayesian mechanisms. |
Jing Chen; Bo Li; Yingkai Li; Pinyan Lu; |
796 | Overlapping Communities and Roles in Networks with Node Attributes: Probabilistic Graphical Modeling, Bayesian Formulation and Variational Inference (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In particular, we focus on unifying the two tasks, by explicitly harnessing node attributes and behavioral role patterns in a principled manner. To this end, we propose two Bayesian probabilistic generative models of networks, whose novelty consists in the interrelationship of overlapping communities, roles, their behavioral patterns and node attributes. |
Gianni Costa; Riccardo Ortale; |
797 | On Quantifying Literals in Boolean Logic and Its Applications to Explainable AI (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Quantified Boolean logic results from adding operators to Boolean logic for existentially and universally quantifying variables. This extends the reach of Boolean logic by … |
Adnan Darwiche; Pierre Marquis; |
798 | Situation Calculus for Controller Synthesis in Manufacturing Systems with First-Order State Representation (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We identify two important decidable cases—finite domains and bounded action theories—for which we provide practical synthesis techniques. |
Giuseppe De Giacomo; Paolo Felli; Brian Logan; Fabio Patrizi; Sebastian Sardiña; |
799 | Making Sense of Raw Input (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The central contribution of this paper is a neuro-symbolic framework for distilling interpretable theories out of streams of raw, unprocessed sensory experience. |
Richard Evans; Matko Bošnjak; Lars Buesing; Kevin Ellis; David Pfau; Pushmeet Kohli; Marek Sergot; |
800 | Abstraction in Data-Sparse Task Transfer (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: These examples highlight the relationship among (i) differences between the source and target environments, (ii) the level of abstraction at which a robot’s task model should be represented to enable transfer to the target environment, and (iii) the information needed to ground the abstracted task representation in the target environment. In this abstract, summarizing our full article [Fitzgerald et al., 2021], we present our taxonomy of transfer problems based on this relationship. |
Tesca Fitzgerald; Ashok Goel; Andrea Thomaz; |
801 | Experimental Comparison and Survey of Twelve Time Series Anomaly Detection Algorithms (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, and especially as the literature continues to expand, an extensive evaluation of every anomaly detection method is simply not feasible. To reduce this evaluation burden, we present guidelines to intelligently choose the optimal anomaly detection methods based on the characteristics the time series displays such as seasonality, trend, level change concept drift, and missing time steps. |
Cynthia Freeman; Jonathan Merriman; Ian Beaver; Abdullah Mueen; |
802 | Dimensional Inconsistency Measures and Postulates in Spatio-Temporal Databases (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We define and investigate new inconsistency measures that are particularly suitable for dealing with inconsistent spatio-temporal information, as they explicitly take into account the spatial and temporal dimensions, as well as the dimension concerning the identifiers of the monitored objects. |
John Grant; Maria Vanina Martinez; Cristian Molinaro; Francesco Parisi; |
803 | Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Maps (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we explore a combination of explanations that attempt to convey the global behavior of the agent and local explanations which provide information regarding the agent’s decision-making in a particular state. |
Tobias Huber; Katharina Weitz; Elisabeth André; Ofra Amir; |
804 | Sunny-as2: Enhancing SUNNY for Algorithm Selection (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work we present sunny-as2, an enhancement of SUNNY for generic AS scenarios that advances the original approach with wrapper-based feature selection, neighborhood-size configuration and a greedy approach to speed-up the training phase. |
Tong Liu; Roberto Amadini; Maurizio Gabbrielli; Jacopo Mauro; |
805 | Intelligence in Strategic Games (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: If an agent, or a coalition of agents, has a strategy, knows that she has a strategy, and knows what the strategy is, then she has a know-how strategy. Several modal logics of … |
Pavel Naumov; Yuan Yuan; |
806 | Learning Realistic Patterns from Visually Unrealistic Stimuli: Generalization and Data Anonymization (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, in many domains existing data sets cannot be shared due to privacy regulations (e.g., from medical studies). This work investigates a simple yet unconventional approach for anonymized data synthesis to enable third parties to benefit from such anonymized data. |
Konstantinos Nikolaidis; Stein Kristiansen; Thomas Plagemann; Vera Goebel; Knut Liestøl; Mohan Kankanhalli; Gunn-Marit Traaen; Britt Øverland; Harriet Akre; Lars Aakeroy; Sigurd Steinshamn; |
807 | Abstraction for Non-Ground Answer Set Programs (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce a notion for abstracting from the domain of an ASP program that shrinks the domain size and over-approximates the set of answer sets, as well as an abstraction-&-refinement methodology that, starting from an initial abstraction, automatically yields an abstraction with an associated answer set matching an answer set of the original program if one exists. |
Zeynep G. Saribatur; Thomas Eiter; Peter Schüller; |
808 | A Theoretical Perspective on Hyperdimensional Computing (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a novel mathematical framework that unifies analysis of HD computing architectures, and provides general, non-asymptotic, sufficient conditions under which HD information processing techniques will succeed. |
Anthony Thomas; Sanjoy Dasgupta; Tajana Rosing; |
809 | Measuring The Occupational Impact of AI: Tasks, Cognitive Abilities and AI Benchmarks (Extended Abstract)* Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a framework for analysing the impact of AI on occupations. |
Songül Tolan; Annarosa Pesole; Fernando Martínez-Plumed; Enrique Fernández-Macías; José Hernández-Orallo; Emilia Gómez; |
810 | Why Bad Coffee? Explaining BDI Agent Behaviour with Valuings (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a formal framework for constructing explanations of the behaviour of an autonomous system, present an (implemented) algorithm for giving explanations, and present evaluation results. |
Michael Winikoff; Galina Sidorenko; Virginia Dignum; Frank Dignum; |
811 | Ethics and Governance of Artificial Intelligence: A Survey of Machine Learning Researchers (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Nevertheless, this influential group’s attitudes are not well understood, undermining our ability to discern consensuses or disagreements between AI/ML researchers. To examine these researchers’ views, we conducted a survey of those who published in two top AI/ML conferences (N = 524). |
Baobao Zhang; Markus Anderljung; Lauren Kahn; Noemi Dreksler; Michael C. Horowitz; Allan Dafoe; |
812 | Improving The Effectiveness and Efficiency of Stochastic Neighbour Embedding with Isolation Kernel (Extended Abstract) Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper presents a new insight into improving the performance of Stochastic Neighbour Embedding (t-SNE) by using Isolation kernel instead of Gaussian kernel. |
Ye Zhu; Kai Ming Ting; |
813 | Irrational, But Adaptive and Goal Oriented: Humans Interacting with Autonomous Agents Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Currently, such agents usually take one of the following approaches for considering human behavior. Some methods assume either a fully cooperative or a zero-sum setting; these assumptions entail that the human’s goals are either identical to that of the agent, or their opposite. |
Amos Azaria; |
814 | Analyzing and Designing Strategic Environments in Social Domains Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: For analyzing multi-agent interaction, we will discuss several computational game-theoretic models to capture various agent characteristics and social (e.g., self-organization) domains. |
Hau Chan; |
815 | Integrating Machine Learning and Optimization to Boost Decision Making Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper presents a conceptual review of our recent advancements in the integration of machine learning and optimization. |
Ferdinando Fioretto; |
816 | Interaction and Expressivity in Collective Decision-Making Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper I present ongoing research on two settings: iterative voting, which repeatedly applies a voting rule until decision-makers converge to an outcome, and delegative voting on multiple issues. |
Umberto Grandi; |
817 | Counting, Sampling, and Synthesis: The Quest for Scalability Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We will discuss our work focused on the development of the next generation of automated reasoning techniques that can perform higher-order tasks such as quantitative measurement, sampling of representative behavior, and automated synthesis of systems. |
Kuldeep S. Meel; |
818 | Controllable Text Generation for Open-Domain Creativity and Fairness Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, I introduce our recent works on controllable text generation to enhance the creativity and fairness of language generation models. |
Nanyun (Violet) Peng; |
819 | Towards Theoretically Grounded Evolutionary Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, I will review the progress towards theoretically grounded evolutionary learning, from the aspects of analysis methodology, theoretical perspectives and learning algorithms. |
Chao Qian; |
820 | Mechanism Design Powered By Social Interactions: A Call to Arms Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: Mechanism design has traditionally assumed that the participants are fixed and independent. However, in reality, the participants are well-connected (e.g., via their social … |
Dengji Zhao; |
821 | Towards New Optimized Artificial Immune Recognition Systems Under The Belief Function Theory Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We opt also in this article for an optimization over the classical AIRS approaches in order to enhance the classification performance. |
Rihab Abdelkhalek; |
822 | Extending Decision Tree to Handle Multiple Fairness Criteria Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a novel, flexible, discrimination-aware classifier that allows the user to: (i) select and mitigate the desired fairness criterion from a set of available options; (ii) implement more than one fairness criterion; (iii) handle more than one sensitive attribute; and (iv) specify the desired level of fairness to meet specific business needs or regulatory requirements. |
Alessandro Castelnovo; |
823 | Dynamic Bandits with Temporal Structure Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we study a dynamic multi-armed bandit (MAB) problem, where the expected reward of each arm evolves over time following an auto-regressive model. |
Qinyi Chen; |
824 | Hybrid Learning System for Large-scale Medical Image Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Adequate annotated data cannot always be satisfied in medical imaging applications. To address such a challenge, we would explore ways to reduce the quality and quantity of annotations requirements of the deep learning model by developing a hybrid learning system. |
Zehua Cheng; Lianlong Wu; |
825 | KRAKEN: A Novel Semantic-Based Approach for Keyphrases Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose KRAKEN, a novel approach for the extraction of keyphrases from texts. |
Simone D’Amico; |
826 | Building A Visual Semantics Aware Object Hierarchy Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Since linguistically annotated images are extensively used for training machine learning models, semantic gap problem (SGP) also results in inevitable bias on image annotations and further leads to poor performance on current computer vision tasks. To address this problem, we propose a novel unsupervised method to build visual semantics aware object hierarchy, aiming to get a classification model by learning from pure-visual information and to dissipate the bias of linguistic representations caused by SGP. |
Xiaolei Diao; |
827 | Decomposition Methods for Solving Scheduling Problem Using Answer Set Programming Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This study proposes solving scheduling problems in industrial applications using the decomposition approach. |
Mohammed M. S. El-Kholany; |
828 | Decentralized Autonomous Organizations and Multi-agent Systems for Artificial Intelligence Applications and Data Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The Ph.D research project aims to explore the potential of the Decentralized Autonomous Organization paradigm in conjunction with classic software architectures for Artificial Intelligence applications. |
Sante Dino Facchini; |
829 | A Unified Framework for Intrinsic Evaluation of Word-Embedding Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Though there are well-established procedures and benchmarks for intrinsic evaluation, as far as we know, a unified method of evaluation that can merge the results of those tasks to provide a comprehensive evaluation is missing. The main goal of this work is to create a pipeline to blend all major intrinsic evaluation tasks to compute such overall evaluation – the PCE – of word embeddings. |
Anna Giabelli; |
830 | Early Diagnosis of Lyme Disease By Recognizing Erythema Migrans Skin Lesion from Images Utilizing Deep Learning Techniques Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our research contribution includes dealing with lack of data, multimodal learning incorporating expert opinion elicitation, and automation of skin hair mask generation. |
Sk Imran Hossain; |
831 | Scalable ML Methods to Optimize KPIs in Real-World Manufacturing Processes Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The goal of this work is to develop novel methods to solve the semiconductor fab scheduling problem. |
Benjamin Kovács; |
832 | Equilibria in Strategic Nominee Selection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In my PhD project I explore the game-theoretic problems related to the strategic selection of party nominees. I aim at establishing the complexity of computational problems in this setting. |
Grzegorz Lisowski; |
833 | Engineering Socially-Oriented Autonomous Agents and Multiagent Systems Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The emergent field of social AI is concerned with the development of autonomous agents that are able to act as part of larger community. Within this context, my research seeks to engineer meaningful social interactions among a group of agents from two different approaches. |
Nieves Montes; |
834 | Application of Neurosymbolic AI to Sequential Decision Making Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: In the history of AI, two main paradigms have been proposed to solve Sequential Decision Making (SDM) problems: Automated Planning (AP) and Reinforcement Learning (RL). Among the … |
Carlos Núñez-Molina; |
835 | Multivariate Times Series Classification Using Multichannel CNN Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To verify the efficacy of the proposed method, we compared it with recent deep learning-based time series classification models on five datasets with small amounts of training data. |
YongKyung Oh; |
836 | Anchors Selection for Cross-lingual Embedding Alignment Through Time Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: In recent years, vector representations of words have proven to be extremely useful across a wide range of NLP applications. Because of the broad interest in the topic, it became … |
Filippo Pallucchini; |
837 | Transferability and Stability of Learning with Limited Labelled Data in Multilingual Text Document Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We focus on learning with limited labelled data (especially meta-learning) in conjunction with so-far under-researched multilingual textual document classification. |
Branislav Pecher; |
838 | Towards Contextually Sensitive Analysis of Memes: Meme Genealogy and Knowledge Base Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This research proposes to a ‘meme genealogy’ of key features and relationships between memes to inform a knowledge base constructed from meme-specific online sources and embed connotative meaning or contextual information in memes. |
Victoria Sherratt; |
839 | Data-Efficient Algorithms and Neural Natural Language Processing: Applications in The Healthcare Domain Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This PhD project introduces novel natural language processing (NLP) use cases in the healthcare domain where obtaining a large training dataset is difficult and expensive. To this end, we propose data-efficient algorithms to fine-tune NLP models in low-resource settings and validate their effectiveness. |
Heereen Shim; |
840 | A Model-Oriented Approach for Lifting Symmetry-Breaking Constraints in Answer Set Programming Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we aim to automatically generalise the discarding of symmetric solutions of Answer Set Programming instances, improving the efficiency of the programs with first-order constraints derived from propositional symmetry-breaking constraints. |
Alice Tarzariol; |
841 | Adaptive Artificial Intelligence Scheduling Methods for Large-Scale, Stochastic, Industrial Applications Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose to develop adaptive algorithms that can leverage the similarities between instances of industrial scheduling problems. |
Pierre Tassel; |
842 | Information Injection to Deep Learning Solutions in Knowledge Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In my thesis, I would like to focus on another approach, where I would not modify the given data nor introduce new architectures, instead, I would like to propose new ways of injecting additional information into knowledge transfer models to increase their performance. |
Paulina Tomaszewska; |
843 | Automatic Multimodal Emotion Recognition Using Facial Expression, Voice, and Text Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This research project aims to develop an automatic emotion recognition system based on facial expression, voice, and words. |
Hélène Tran; |
844 | Anomaly Explanation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we demonstrate the importance of anomaly explanation, the areas still needing investigation based upon our previous contributions to the field, and the future directions that will be explored. |
Véronne Yepmo; |
845 | Diffusion Incentives in Cooperative Games Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our goal cannot be achieved by existing classical solutions, such as the Shapley value. Hence, to combat this problem, we have already proposed a solution called weighted permission Shapley value. |
Yao Zhang; |
846 | Together About Dementia Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present “Together about Dementia”, a mobile health app that aims to help persons with dementia when they get lost through the help of caregivers, relatives, and volunteering citizens. |
Nicklas Sindlev Andersen; Marco Chiarandini; |
847 | Displaying Justifications for Collective Decisions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present an online demonstration tool illustrating a general approach to computing justifications for accepting a given decision when confronted with the preferences of several agents. |
Arthur Boixel; Ulle Endriss; Oliviero Nardi; |
848 | Itero: An Online Iterative Voting Application Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper presents our implementation of iterative voting on a voting platform accessible on the web. |
Joseph Boudou; Rachael Colley; Umberto Grandi; |
849 | Interactive Reinforcement Learning for Symbolic Regression from Multi-Format Human-Preference Feedbacks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose an interactive platform to perform grammar-guided symbolic regression using a reinforcement learning approach from human-preference feedback. |
Laure Crochepierre; Lydia Boudjeloud-Assala; Vincent Barbesant; |
850 | Knowledge-Based News Event Analysis and Forecasting Toolkit Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a toolkit for knowledge-based news event analysis and forecasting. |
Oktie Hassanzadeh; Parul Awasthy; Ken Barker; Onkar Bhardwaj; Debarun Bhattacharjya; Mark Feblowitz; Lee Martie; Jian Ni; Kavitha Srinivas; Lucy Yip; |
851 | CARBEN: Composite Adversarial Robustness Benchmark Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper demonstrates how CAA’s attack order affects the resulting image, and provides real-time inferences of different models, which will facilitate users’ configuration of the parameters of the attack level and their rapid evaluation of model prediction. |
Lei Hsiung; Yun-Yun Tsai; Pin-Yu Chen; Tsung-Yi Ho; |
852 | A Speech-driven Sign Language Avatar Animation System for Hearing Impaired Applications Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a system-level scheme and push forward the implementation of sign language production for practical usage. |
Li Hu; Jiahui Li; Jiashuo Zhang; Qi Wang; Bang Zhang; Ping Tan; |
853 | ExplainIt!: A Tool for Computing Robust Attributions of DNNs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present ExplainIt, an online tool for explaining AI decisions that uses neural SDEs to create visually sharper and more robust attributions than traditional residual neural networks. |
Sumit Jha; Alvaro Velasquez; Rickard Ewetz; Laura Pullum; Susmit Jha; |
854 | PillGood: Automated and Interactive Pill Dispenser Using Facial Recognition for Safe and Personalized Medication Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To help patients get accurate medication following their prescription plan with minimizing human labors and mistakes, we developed PillGood, an automated smart pill dispenser system using facial recognition technique. |
Jonghyeok Kim; Hosung Kwon; Jonghyeon Kim; Jinsoo Park; Soong-Un Choi; Sookyung Kim; |
855 | Sign-to-Speech Model for Sign Language Understanding: A Case Study of Nigerian Sign Language Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Through this paper, we seek to reduce the communication barrier between the hearing-impaired community and the larger society who are usually not familiar with sign language in the sub-Saharan region of Africa with the largest occurrences of hearing disability cases, while using Nigeria as a case study. |
Steven Kolawole; Opeyemi Osakuade; Nayan Saxena; Babatunde Kazeem Olorisade; |
856 | Real-Time Portrait Stylization on The Edge Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work we demonstrate real-time portrait stylization, specifically, translating self-portrait into cartoon or anime style on mobile devices. |
Yanyu Li; Xuan Shen; Geng Yuan; Jiexiong Guan; Wei Niu; Hao Tang; Bin Ren; Yanzhi Wang; |
857 | AMICA: An Argumentative Search Engine for COVID-19 Literature Related Papers Related Patents Related Grants Related Orgs Related Experts View Abstract: AMICA is an argument mining-based search engine, specifically designed for the analysis of scientific literature related to Covid-19. AMICA retrieves scientific papers based on … |
Marco Lippi; Francesco Antici; Gianfranco Brambilla; Evaristo Cisbani; Andrea Galassi; Daniele Giansanti; Fabio Magurano; Antonella Rosi; Federico Ruggeri; Paolo Torroni; |
858 | The Good, The Bad, and The Explainer: A Tool for Contrastive Explanations of Text Classifiers Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we demonstrate ContrXT, a novel tool that computes the differences in the classification logic of two distinct trained models, reasoning on their symbolic representation through Binary Decision Diagrams. |
Lorenzo Malandri; Fabio Mercorio; Mario Mezzanzanica; Navid Nobani; Andrea Seveso; |
859 | ACTA 2.0: A Modular Architecture for Multi-Layer Argumentative Analysis of Clinical Trials Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: ACTA 2.0 is an automated tool which relies on Argument Mining methods to analyse the abstracts of clinical trials to extract argument components and relations to support evidence-based clinical decision making. |
Benjamin Molinet; Santiago Marro; Elena Cabrio; Serena Villata; Tobias Mayer; |
860 | VMAgent: A Practical Virtual Machine Scheduling Platform Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we design a practical VM scheduling platform, i.e., VMAgent, to assist researchers in developing their methods on the VM scheduling problem. |
Junjie Sheng; Shengliang Cai; Haochuan Cui; Wenhao Li; Yun Hua; Bo Jin; Wenli Zhou; Yiqiu Hu; Lei Zhu; Qian Peng; Hongyuan Zha; Xiangfeng Wang; |
861 | Fine-tuning Deep Neural Networks By Interactively Refining The 2D Latent Space of Ambiguous Images Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: By contrast, humans have a relatively good ability to distinguish these categories of images. Therefore, we propose a human-in-the-loop solution to assist the network to better classify the images by leveraging human knowledge. |
Jiafu Wei; Haoran Xie; Chia-Ming Chang; Xi Yang; |
862 | AutoVideo: An Automated Video Action Recognition System Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, developing an effective action recognition solution often requires extensive engineering efforts in building and testing different combinations of the modules and their hyperparameters. In this demo, we present AutoVideo, a Python system for automated video action recognition. |
Daochen Zha; Zaid Pervaiz Bhat; Yi-Wei Chen; Yicheng Wang; Sirui Ding; Jiaben Chen; Kwei-Herng Lai; Mohammad Qazim Bhat; Anmoll Kumar Jain; Alfredo Costilla Reyes; Na Zou; Xia Hu; |
863 | Text/Speech-Driven Full-Body Animation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we present a production-ready text/speech-driven full-body animation synthesis system. |
Wenlin Zhuang; Jinwei Qi; Peng Zhang; Bang Zhang; Ping Tan; |