Paper Digest: KDD 2022 Highlights
Download KDD-2022-Paper-Digests.pdf– highlights of all KDD-2022 papers. Paper 1-3 are keynote talks; 4-256 are research track papers, 257-452 are ADS track papers, and 453-462 are health day papers. Readers can choose to read all these highlights on our console, which allows users to filter out papers using keywords and find related papers, patents, etc. In addition, we identified more than 120 papers that have published their code. Clicking on ‘related code’ link under paper title will take you directly to the codebase. To browse papers by author, here is a list of top KDD-2022 authors. You may also like to explore our “Best Paper” Digest (KDD), which lists the most influential KDD papers since 1999.
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) is one of the top data mining conferences in the world. In 2022, it is to be held in Washington, DC.
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: KDD 2022 Highlights
| Paper | Author(s) | |
|---|---|---|
| 1 | The Power of (Statistical) Relational Thinking Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this talk, I will give an introduction to the field of Statistical Relational Learning (SRL), and I’ll identify useful tips and tricks for exploiting structure in both the input and output space. |
Lise Getoor; |
| 2 | AI for Social Impact: Results from Deployments for Public Health and Conversation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: I will focus on domains of public health and conservation, and address one key cross-cutting challenge: how to effectively deploy our limited intervention resources in these problem domains. I will present results from work around the globe in using AI for challenges in public health such as Maternal and Child care interventions, HIV prevention, and in conservation such as endangered wildlife protection. |
Milind Tambe; |
| 3 | Beyond Traditional Characterizations in The Age of Data: Big Models, Scalable Algorithms, and Meaningful Solutions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Thus, scalability, not just polynomial-time computability, should be elevated as the central complexity notion for characterizing efficient computation. In this talk, I will discuss some aspects of these challenges. |
Shang-Hua Teng; |
| 4 | GBPNet: Universal Geometric Representation Learning on Protein Structures Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we introduce geometric bottleneck perceptron, and a general SO(3)-equivariant message passing neural network built on top of it for protein structure representation learning. |
Sarp Aykent; Tian Xia; |
| 5 | Saliency-Regularized Deep Multi-Task Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To address these challenges, this paper proposes a new multi-task learning framework that jointly learns latent features and explicit task relations by complementing the strength of existing shallow and deep multitask learning scenarios. |
Guangji Bai; Liang Zhao; |
| 6 | Submodular Feature Selection for Partial Label Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, the first attempt towards partial label feature selection is investigated via mutual-information-based dependency maximization. |
Wei-Xuan Bao; Jun-Yi Hang; Min-Ling Zhang; |
| 7 | Motif Prediction with Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We first show that existing link prediction schemes fail to effectively predict motifs. To alleviate this, we establish a general motif prediction problem and we propose several heuristics that assess the chances for a specified motif to appear. |
Maciej Besta; Raphael Grob; Cesare Miglioli; Nicola Bernold; Grzegorz Kwasniewski; Gabriel Gjini; Raghavendra Kanakagiri; Saleh Ashkboos; Lukas Gianinazzi; Nikoli Dryden; Torsten Hoefler; |
| 8 | Practical Lossless Federated Singular Vector Decomposition Over Billion-Scale Data Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose FedSVD, a practical lossless federated SVD method over billion-scale data, which can simultaneously achieve lossless accuracy and high efficiency. |
Di Chai; Leye Wang; Junxue Zhang; Liu Yang; Shuowei Cai; Kai Chen; Qiang Yang; |
| 9 | Avoiding Biases Due to Similarity Assumptions in Node Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Our proposed embedding, called NEWS, makes no similarity assumptions, avoiding potential risks to privacy and fairness. |
Deepayan Chakrabarti; |
| 10 | Open-Domain Aspect-Opinion Co-Mining with Double-Layer Span Extraction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose an Open-Domain Aspect-Opinion Co-Mining (ODAO) method with a Double-Layer span extraction framework. |
Mohna Chakraborty; Adithya Kulkarni; Qi Li; |
| 11 | Multi-Variate Time Series Forecasting on Variable Subsets Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose a non-parametric, wrapper technique that can be applied on top any existing forecast models. |
Jatin Chauhan; Aravindan Raghuveer; Rishi Saket; Jay Nandy; Balaraman Ravindran; |
| 12 | FedMSplit: Correlation-Adaptive Federated Multi-Task Learning Across Multimodal Split Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we address a novel challenging issue in MFL, the modality incongruity, where clients may have heterogeneous setups of sensors and their local data consists of different combinations of modalities. |
Jiayi Chen; Aidong Zhang; |
| 13 | Efficient Join Order Selection Learning with Graph-based Representation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel framework, namely efficient Join Order selection learninG with Graph-basEd Representation (JOGGER). |
Jin Chen; Guanyu Ye; Yan Zhao; Shuncheng Liu; Liwei Deng; Xu Chen; Rui Zhou; Kai Zheng; |
| 14 | Knowledge-enhanced Black-box Attacks for Recommendations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: More specifically, we propose a knowledge graph-enhanced black-box attacking framework (KGAttack) to effectively learn attacking policies through deep reinforcement learning techniques, in which knowledge graph is seamlessly integrated into hierarchical policy networks to generate fake user profiles for performing adversarial black-box attacks. |
Jingfan Chen; Wenqi Fan; Guanghui Zhu; Xiangyu Zhao; Chunfeng Yuan; Qing Li; Yihua Huang; |
| 15 | Multi-modal Siamese Network for Entity Alignment Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To deal with that problem, in this paper, we propose a novel Multi-modal Siamese Network for Entity Alignment (MSNEA) to align entities in different MMKGs, in which multi-modal knowledge could be comprehensively leveraged by the exploitation of inter-modal effect. |
Liyi Chen; Zhi Li; Tong Xu; Han Wu; Zhefeng Wang; Nicholas Jing Yuan; Enhong Chen; |
| 16 | Efficient Orthogonal Multi-view Subspace Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: How to learn a set of high-quality orthogonal bases in a unified framework, while maintaining its scalability for very large datasets, remains a big challenge. In view of this, we propose an Efficient Orthogonal Multi-view Subspace Clustering (OMSC) model with almost linear complexity. |
Man-Sheng Chen; Chang-Dong Wang; Dong Huang; Jian-Huang Lai; Philip S. Yu; |
| 17 | Scalar Is Not Enough: Vectorization-based Unbiased Learning to Rank Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a vector-based EH and formulate the click probability as a dot product of two vector functions. |
Mouxiang Chen; Chenghao Liu; Zemin Liu; Jianling Sun; |
| 18 | Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address these challenges, we design an innovative framework Quaternion Transformer (Quatformer), along with three major components: 1). learning-to-rotate attention (LRA) based on quaternions which introduces learnable period and phase information to depict intricate periodical patterns. 2). trend normalization to normalize the series representations in hidden layers of the model considering the slowly varying characteristic of trend. 3). decoupling LRA using global memory to achieve linear complexity without losing prediction accuracy. |
Weiqi Chen; Wenwei Wang; Bingqing Peng; Qingsong Wen; Tian Zhou; Liang Sun; |
| 19 | Efficient Approximate Algorithms for Empirical Variance with Hashed Block Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Based on our sampling strategy, we present an approximate algorithm for empirical variance and an approximate top-k algorithm to return the k columns with the highest empirical variance scores. |
Xingguang Chen; Fangyuan Zhang; Sibo Wang; |
| 20 | Learning Binarized Graph Representations with Multi-faceted Quantization Reinforcement for Top-K Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel quantization framework to learn Binarized Graph Representations for Top-K Recommendation (BiGeaR). |
Yankai Chen; Huifeng Guo; Yingxue Zhang; Chen Ma; Ruiming Tang; Jingjie Li; Irwin King; |
| 21 | RLogic: Recursive Logical Rule Learning from Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Instead of completely relying on rule instances for rule evaluation, RLogic defines a predicate representation learning-based scoring model, which is trained by sampled rule instances. In addition, RLogic incorporates one of the most significant properties of logical rules, the deductive nature, into rule learning, which is critical especially when a rule lacks supporting evidence. |
Kewei Cheng; Jiahao Liu; Wei Wang; Yizhou Sun; |
| 22 | Sufficient Vision Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Nevertheless, task-irrelevant information such as background nuisance and noise in patch tokens would damage the performance of ViT-based models. In this paper, we develop Sufficient Vision Transformer (Suf-ViT) as a new solution to address this issue. |
Zhi Cheng; Xiu Su; Xueyu Wang; Shan You; Chang Xu; |
| 23 | HyperAid: Denoising in Hyperbolic Spaces for Tree-fitting and Hierarchical Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: First, we propose a new approach to tree-metric denoising (HyperAid) in hyperbolic spaces which transforms the original data into data that is more” tree-like, when evaluated in terms of Gromov’s d hyperbolicity. Second, we perform an ablation study involving two choices for the approximation objective, lp norms and the Dasgupta loss. Third, we integrate HyperAid with schemes for enforcing nonnegative edge-weights. |
Eli Chien; Puoya Tabaghi; Olgica Milenkovic; |
| 24 | TARNet: Task-Aware Reconstruction for Time-Series Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose TARNet, Task-Aware Reconstruction Network, a new model using Transformers to learn task-aware data reconstruction that augments end-task performance. |
Ranak Roy Chowdhury; Xiyuan Zhang; Jingbo Shang; Rajesh K. Gupta; Dezhi Hong; |
| 25 | Scalable Differentially Private Clustering Via Hierarchically Separated Trees Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We study the private k-median and k-means clustering problem in d dimensional Euclidean space. |
Vincent Cohen-Addad; Alessandro Epasto; Silvio Lattanzi; Vahab Mirrokni; Andres Munoz Medina; David Saulpic; Chris Schwiegelshohn; Sergei Vassilvitskii; |
| 26 | Noisy Interactive Graph Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our objective in this problem is to minimize the query complexity while ensuring accuracy. We propose a method to select the query node such that we can push the search process as much as possible and an online method to infer which node is the target after collecting a new answer. |
Qianhao Cong; Jing Tang; Kai Han; Yuming Huang; Lei Chen; Yeow Meng Chee; |
| 27 | Collaboration Equilibrium in Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose the concept of benefit graph which describes how each client can benefit from collaborating with other clients and advance a Pareto optimization approach to identify the optimal collaborators. |
Sen Cui; Jian Liang; Weishen Pan; Kun Chen; Changshui Zhang; Fei Wang; |
| 28 | A Generalized Doubly Robust Learning Framework for Debiasing Post-Click Conversion Rate Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Based on the framework, we propose two new DR methods, namely DR-BIAS and DR-MSE. |
Quanyu Dai; Haoxuan Li; Peng Wu; Zhenhua Dong; Xiao-Hua Zhou; Rui Zhang; Rui Zhang; Jie Sun; |
| 29 | Discovering Significant Patterns Under Sequential False Discovery Control Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We are interested in discovering those patterns from data with an empirical frequency that is significantly differently than expected. |
Sebastian Dalleiger; Jilles Vreeken; |
| 30 | Debiasing The Cloze Task in Sequential Recommendation with Bidirectional Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we argue and prove that IPS does not extend to sequential recommendation because it fails to account for the temporal nature of the problem. |
Khalil Damak; Sami Khenissi; Olfa Nasraoui; |
| 31 | Framing Algorithmic Recourse for Anomaly Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present an approach-Context preserving Algorithmic Recourse for Anomalies in Tabular data(CARAT), that is effective, scalable, and agnostic to the underlying anomaly detection model. |
Debanjan Datta; Feng Chen; Naren Ramakrishnan; |
| 32 | Robust Event Forecasting with Spatiotemporal Confounder Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we introduce a deep learning framework that integrates causal effect estimation into event forecasting. |
Songgaojun Deng; Huzefa Rangwala; Yue Ning; |
| 33 | Addressing Unmeasured Confounder for Recommendation with Sensitivity Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This work combats the risk of unmeasured confounders in recommender systems. Towards this end, we propose Robust Deconfounder (RD) that accounts for the effect of unmeasured confounders on propensities, under the mild assumption that the effect is bounded. |
Sihao Ding; Peng Wu; Fuli Feng; Yitong Wang; Xiangnan He; Yong Liao; Yongdong Zhang; |
| 34 | On Structural Explanation of Bias in Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we study a novel research problem of structural explanation of bias in GNNs. |
Yushun Dong; Song Wang; Yu Wang; Tyler Derr; Jundong Li; |
| 35 | Fair Labeled Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To ensure group fairness in such a setting, we would desire proportional group representation in every label but not necessarily in every cluster as is done in group fair clustering. We provide algorithms for such problems and show that in contrast to their NP-hard counterparts in group fair clustering, they permit efficient solutions. |
Seyed A. Esmaeili; Sharmila Duppala; John P. Dickerson; Brian Brubach; |
| 36 | On Aligning Tuples for Regression Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To deal with timestamp variations, existing time series matching techniques rely on the similarity of values and timestamps, which unfortunately are very likely to be absent among the variables in regression (no similarity between engine torque and speed values). In this sense, we propose to bridge tuple alignment and regression. |
Chenguang Fang; Shaoxu Song; Yinan Mei; Ye Yuan; Jianmin Wang; |
| 37 | Spatio-Temporal Trajectory Similarity Learning in Road Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, existing learning-based trajectory similarity learning solutions prioritize spatial similarity over temporal similarity, making them suboptimal for time-aware analyses. To this end, we propose ST2Vec, a representation learning based solution that considers fine-grained spatial and temporal relations between trajectories to enable spatio-temporal similarity computation in road networks. |
Ziquan Fang; Yuntao Du; Xinjun Zhu; Danlei Hu; Lu Chen; Yunjun Gao; Christian S. Jensen; |
| 38 | FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose the first Free-direction Knowledge Distillation framework via Reinforcement learning for GNNs, called FreeKD, which is no longer required to provide a deeper well-optimized teacher GNN. The core idea of our work is to collaboratively build two shallower GNNs in an effort to exchange knowledge between them via reinforcement learning in a hierarchical way. |
Kaituo Feng; Changsheng Li; Ye Yuan; Guoren Wang; |
| 39 | Meta-Learned Metrics Over Multi-Evolution Temporal Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To learn a good metric over temporal graphs, we propose a temporal graph metric learning framework, Temp-GFSM. |
Dongqi Fu; Liri Fang; Ross Maciejewski; Vetle I. Torvik; Jingrui He; |
| 40 | SIPF: Sampling Method for Inverse Protein Folding Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address the issues, we propose a sampling method for inverse protein folding (SIPF). |
Tianfan Fu; Jimeng Sun; |
| 41 | Antibody Complementarity Determining Regions (CDRs) Design Using Constrained Energy Model Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, the existing methods faced the challenges of maintaining the specific geometry shape of the CDR loops. This paper proposes a Constrained Energy Model (CEM) to address this issue. |
Tianfan Fu; Jimeng Sun; |
| 42 | Optimal Interpretable Clustering Using Oblique Decision Trees Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Here, we focus on the relatively unexplored case of interpretable clustering. |
Magzhan Gabidolla; Miguel Á. Carreira-Perpiñán; |
| 43 | Finding Meta Winning Ticket to Train Your MAML Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, to achieve rapid learning with less computational cost, we explore LTH in the context of meta learning. |
Dawei Gao; Yuexiang Xie; Zimu Zhou; Zhen Wang; Yaliang Li; Bolin Ding; |
| 44 | ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, the increasing scale of KGs renders it hard for EA models to adopt the normalization processes, thus limiting their usage in real-world applications. To tackle this challenge, we present ClusterEA, a general framework that is capable of scaling up EA models and enhancing their results by leveraging normalization methods on mini-batches with a high entity equivalent rate. |
Yunjun Gao; Xiaoze Liu; Junyang Wu; Tianyi Li; Pengfei Wang; Lu Chen; |
| 45 | RES: A Robust Framework for Guiding Visual Explanation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To address the challenges, we propose a generic RES framework for guiding visual explanation by developing a novel objective that handles inaccurate boundary, incomplete region, and inconsistent distribution of human annotations, with a theoretical justification on model generalizability. |
Yuyang Gao; Tong Steven Sun; Guangji Bai; Siyi Gu; Sungsoo Ray Hong; Zhao Liang; |
| 46 | Disentangled Ontology Embedding for Zero-shot Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we focus on ontologies for augmenting ZSL, and propose to learn disentangled ontology embeddings guided by ontology properties to capture and utilize more fine-grained class relationships in different aspects. |
Yuxia Geng; Jiaoyan Chen; Wen Zhang; Yajing Xu; Zhuo Chen; Jeff Z. Pan; Yufeng Huang; Feiyu Xiong; Huajun Chen; |
| 47 | PARSRec: Explainable Personalized Attention-fused Recurrent Sequential Recommendation Using Session Partial Actions Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This approach, while effective, is oblivious to subtle idiosyncrasies that differentiate humans from each other. Focusing on this observation, we propose an architecture that relies on common patterns as well as individual behaviors to tailor its recommendations for each person. |
Ehsan Gholami; Mohammad Motamedi; Ashwin Aravindakshan; |
| 48 | Robust Inverse Framework Using Knowledge-guided Self-Supervised Learning: An Application to Hydrology Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Existing basin characteristics suffer from noise and uncertainty, among many other things, which adversely impact model performance. To tackle the above challenges, in this paper, we propose a novel Knowledge-guided Self-Supervised Learning (KGSSL) inverse framework to extract system characteristics from driver(input) and response(output) data. |
Rahul Ghosh; Arvind Renganathan; Kshitij Tayal; Xiang Li; Ankush Khandelwal; Xiaowei Jia; Christopher Duffy; John Nieber; Vipin Kumar; |
| 49 | Subset Node Anomaly Tracking Over Large Dynamic Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper proposes DynAnom, an efficient framework to quantify the changes and localize per-node anomalies over large dynamic weighted-graphs. |
Xingzhi Guo; Baojian Zhou; Steven Skiena; |
| 50 | BLISS: A Billion Scale Index Using Iterative Re-partitioning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To improve the trade-off, we propose a new algorithm, called BaLanced Index for Scalable Search (BLISS), a highly tunable indexing algorithm with enviably small index sizes, making it easy to scale to billions of vectors. |
Gaurav Gupta; Tharun Medini; Anshumali Shrivastava; Alexander J. Smola; |
| 51 | ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we present ProActive, a neural marked temporal point process (MTPP) framework for modeling the continuous-time distribution of actions in an activity sequence while simultaneously addressing three high-impact problems – next action prediction, sequence-goal prediction, and end-to-end sequence generation. |
Vinayak Gupta; Srikanta Bedathur; |
| 52 | Connecting Low-Loss Subspace for Personalized Federated Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We proposed SuPerFed, a personalized federated learning method that induces an explicit connection between the optima of the local and the federated model in weight space for boosting each other. |
Seok-Ju Hahn; Minwoo Jeong; Junghye Lee; |
| 53 | Continuous-Time and Multi-Level Graph Representation Learning for Origin-Destination Demand Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Among them, the pairwise Origin-Destination (OD) demand prediction is a valuable but challenging problem due to several factors: (i) the large number of possible OD pairs, (ii) implicitness of spatial dependence, and (iii) complexity of traffic states. To address the above issues, this paper proposes a Continuous-time and Multi-level dynamic graph representation learning method for Origin-Destination demand prediction (CMOD). |
Liangzhe Han; Xiaojian Ma; Leilei Sun; Bowen Du; Yanjie Fu; Weifeng Lv; Hui Xiong; |
| 54 | Streaming Hierarchical Clustering Based on Point-Set Kernel Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This is because they rely on pairwise point-based similarity calculations and the similarity measure is independent of data distribution. In this paper, we aim to overcome these weaknesses and propose a novel efficient hierarchical clustering called StreaKHC that enables massive streaming data to be mined. |
Xin Han; Ye Zhu; Kai Ming Ting; De-Chuan Zhan; Gang Li; |
| 55 | Compressing Deep Graph Neural Networks Via Adversarial Knowledge Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, using the same distance for graphs of various structures may be unfit, and the optimal distance formulation is hard to determine. To tackle these problems, we propose a novel Adversarial Knowledge Distillation framework for graph models named GraphAKD, which adversarially trains a discriminator and a generator to adaptively detect and decrease the discrepancy. |
Huarui He; Jie Wang; Zhanqiu Zhang; Feng Wu; |
| 56 | Partial Label Learning with Semantic Label Representations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel framework partial label learning with semantic label representations dubbed ParSE, which consists of two synergistic processes, including visual-semantic representation learning and powerful label disambiguation. |
Shuo He; Lei Feng; Fengmao Lv; Wen Li; Guowu Yang; |
| 57 | Quantifying and Reducing Registration Uncertainty of Spatial Vector Labels on Earth Imagery Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To fill the gap, this paper proposes a novel learning framework that explicitly quantifies vector labels’ registration uncertainty. |
Wenchong He; Zhe Jiang; Marcus Kriby; Yiqun Xie; Xiaowei Jia; Da Yan; Yang Zhou; |
| 58 | Core-periphery Partitioning and Quantum Annealing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a new kernel that quantifies success for the task of computing a core-periphery partition for an undirected network. |
Catherine F. Higham; Desmond J. Higham; Francesco Tudisco; |
| 59 | AdaAX: Explaining Recurrent Neural Networks By Learning Automata with Adaptive States Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a new method to construct deterministic finite automata to explain RNN. |
Dat Hong; Alberto Maria Segre; Tong Wang; |
| 60 | Towards Universal Sequence Representation Learning for Recommender Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In order to develop effective sequential recommenders, a series of sequence representation learning (SRL) methods are proposed to model historical user behaviors. |
Yupeng Hou; Shanlei Mu; Wayne Xin Zhao; Yaliang Li; Bolin Ding; Ji-Rong Wen; |
| 61 | GraphMAE: Self-Supervised Masked Graph Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we identify and examine the issues that negatively impact the development of GAEs, including their reconstruction objective, training robustness, and error metric. |
Zhenyu Hou; Xiao Liu; Yukuo Cen; Yuxiao Dong; Hongxia Yang; Chunjie Wang; Jie Tang; |
| 62 | Few-Shot Fine-Grained Entity Typing with Automatic Label Interpretation and Instance Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose a novel framework for few-shot FET consisting of two modules: (1) an entity type label interpretation module automatically learns to relate type labels to the vocabulary by jointly leveraging few-shot instances and the label hierarchy, and (2) a type-based contextualized instance generator produces new instances based on given instances to enlarge the training set for better generalization. |
Jiaxin Huang; Yu Meng; Jiawei Han; |
| 63 | LinE: Logical Query Reasoning Over Hierarchical Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To bridge the gap, we propose a logical query reasoning framework, Line Embedding (LinE), for FOL queries. |
Zijian Huang; Meng-Fen Chiang; Wang-Chien Lee; |
| 64 | Local Evaluation of Time Series Anomaly Detection Algorithms Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To cope with the above problems, we propose a theoretically grounded, robust, parameter-free and interpretable extension to precision/recall metrics, based on the concept of "affiliation” between the ground truth and the prediction sets. |
Alexis Huet; Jose Manuel Navarro; Dario Rossi; |
| 65 | Low-rank Nonnegative Tensor Decomposition in Hyperbolic Space Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose to decompose tensor in hyperbolic space. |
Bo Hui; Wei-Shinn Ku; |
| 66 | Global Self-Attention As A Replacement for Graph Convolution Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose an extension to the transformer neural network architecture for general-purpose graph learning by adding a dedicated pathway for pairwise structural information, called edge channels. |
Md Shamim Hussain; Mohammed J. Zaki; Dharmashankar Subramanian; |
| 67 | Flexible Modeling and Multitask Learning Using Differentiable Tree Ensembles Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a flexible framework for learning tree ensembles, which goes beyond existing toolkits to support arbitrary loss functions, missing responses, and multi-task learning. |
Shibal Ibrahim; Hussein Hazimeh; Rahul Mazumder; |
| 68 | Dual-Geometric Space Embedding Model for Two-View Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: For works that seek to put both views of the KG together, the instance and ontology views are assumed to belong to the same geometric space, such as all nodes embedded in the same Euclidean space or non-Euclidean product space, an assumption no longer reasonable for two-view KGs where different portions of the graph exhibit different structures. To address this issue, we define and construct a dual-geometric space embedding model (DGS) that models two-view KGs using a complex non-Euclidean geometric space, by embedding different portions of the KG in different geometric spaces. |
Roshni G. Iyer; Yunsheng Bai; Wei Wang; Yizhou Sun; |
| 69 | Detecting Cash-out Users Via Dense Subgraphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we focus on discerning fraudulent cash-out users by taking advantage of only the personal credit card data from banks. |
Yingsheng Ji; Zheng Zhang; Xinlei Tang; Jiachen Shen; Xi Zhang; Guangwen Yang; |
| 70 | A Spectral Representation of Networks: The Path of Subgraphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, sometimes networks with different structures or sizes can have the same or similar spectral moments, not to mention the existence of the cospectral graphs. To address such problems, we propose a 3D network representation that relies on the spectral information of subgraphs: the Spectral Path, a path connecting the spectral moments of the network and those of its subgraphs of different sizes. |
Shengmin Jin; Hao Tian; Jiayu Li; Reza Zafarani; |
| 71 | Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a new perspective to look at the performance degradation of deep GNNs, i.e., feature overcorrelation. |
Wei Jin; Xiaorui Liu; Yao Ma; Charu Aggarwal; Jiliang Tang; |
| 72 | Condensing Graphs Via One-Step Gradient Matching Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To bridge the gap, we investigate efficient dataset condensation tailored for graph datasets where we model the discrete graph structure as a probabilistic model. |
Wei Jin; Xianfeng Tang; Haoming Jiang; Zheng Li; Danqing Zhang; Jiliang Tang; Bing Yin; |
| 73 | Selective Cross-City Transfer Learning for Traffic Prediction Via Source City Region Re-Weighting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address the problem, we propose CrossTReS, a selective transfer learning framework for traffic prediction that adaptively re-weights source regions to assist target fine-tuning. |
Yilun Jin; Kai Chen; Qiang Yang; |
| 74 | JuryGCN: Quantifying Jackknife Uncertainty on Graph Convolutional Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose the first frequentist-based approach named JuryGCN in quantifying the uncertainty of GCN, where the key idea is to quantify the uncertainty of a node as the width of confidence interval by a jackknife estimator. |
Jian Kang; Qinghai Zhou; Hanghang Tong; |
| 75 | HyperLogLogLog: Cardinality Estimation With One Log More Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We present HyperLogLogLog, a practical compression of the HyperLogLog sketch that compresses the sketch from $O(m?og?og n)$ bits down to $m ?og_2?og_2?og_2 m + O(m+?og?og n)$ bits for estimating the number of distinct elements~n using m~registers. |
Matti Karppa; Rasmus Pagh; |
| 76 | SOS: Score-based Oversampling for Tabular Data Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: SGMs are known to surpass other generative models, e.g., generative adversarial networks (GANs) and variational autoencoders (VAEs). Being inspired by their big success, in this work, we fully customize them for generating fake tabular data. |
Jayoung Kim; Chaejeong Lee; Yehjin Shin; Sewon Park; Minjung Kim; Noseong Park; Jihoon Cho; |
| 77 | CoRGi: Content-Rich Graph Neural Networks with Attention Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, when processing graphs with graph neural networks (GNN), such information is either ignored or summarized into a single vector representation used to initialize the GNN. Towards addressing this, we present CoRGi, a GNN that considers the rich data within nodes in the context of their neighbors. |
Jooyeon Kim; Angus Lamb; Simon Woodhead; Simon Peyton Jones; Cheng Zhang; Miltiadis Allamanis; |
| 78 | Learned Token Pruning for Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Efficient deployment of transformer models in practice is challenging due to their inference cost including memory footprint, latency, and power consumption, which scales quadratically with input sequence length. To address this, we present a novel token reduction method dubbed Learned Token Pruning (LTP) which adaptively removes unimportant tokens as an input sequence passes through transformer layers. |
Sehoon Kim; Sheng Shen; David Thorsley; Amir Gholami; Woosuk Kwon; Joseph Hassoun; Kurt Keutzer; |
| 79 | ExMeshCNN: An Explainable Convolutional Neural Network Architecture for 3D Shape Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose ExMeshCNN, a novel and explainable CNN structure for learning 3D meshes. |
Seonggyeom Kim; Dong-Kyu Chae; |
| 80 | In Defense of Core-set: A Density-aware Core-set Selection for Active Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we analyze the feature space through the lens of density and, interestingly, observe that locally sparse regions tend to have more informative samples than dense regions. |
Yeachan Kim; Bonggun Shin; |
| 81 | FlowGEN: A Generative Model for Flow Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce FlowGEN, an implicit generative model for flow graphs, that learns how to jointly generate graph topologies and flows with diverse dynamics directly from data using a novel (flow) graph neural network. |
Furkan Kocayusufoglu; Arlei Silva; Ambuj K. Singh; |
| 82 | Variational Inference for Training Graph Neural Networks in Low-Data Regime Through Joint Structure-Label Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In real-world scenarios where complete input graph structure and sufficient node labels might not be achieved easily, GNN models would encounter with severe performance degradation. To address this problem, we propose WSGNN, short for weakly-supervised graph neural network. |
Danning Lao; Xinyu Yang; Qitian Wu; Junchi Yan; |
| 83 | Modeling Network-level Traffic Flow Transitions on Sparse Data Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we consider the problem of modeling network-level traffic flow under a real-world setting, where the available data is sparse (i.e., only part of the traffic system is observed). |
Xiaoliang Lei; Hao Mei; Bin Shi; Hua Wei; |
| 84 | The DipEncoder: Enforcing Multimodality in Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we show how to apply the gradient not only with respect to the projection axis but also with respect to the data to improve the cluster structure. |
Collin Leiber; Lena G. M. Bauer; Michael Neumayr; Claudia Plant; Christian Böhm; |
| 85 | KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To this end, we introduce Knowledge-guided Pre-training of Graph Transformer (KPGT), a novel self-supervised learning framework for molecular graph representation learning, to alleviate the aforementioned issues and improve the performance on the downstream molecular property prediction tasks. |
Han Li; Dan Zhao; Jianyang Zeng; |
| 86 | Domain Adaptation in Physical Systems Via Graph Kernel Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel cross-graph DA based on two core designs of graph kernels and graph coarsening. |
Haoran Li; Hanghang Tong; Yang Weng; |
| 87 | Sampling-based Estimation of The Number of Distinct Values in Distributed Environment Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper proposes a novel sketch-based distributed method that achieves sub-linear communication costs for distributed sampling-based NDV estimation under mild assumptions. |
Jiajun Li; Zhewei Wei; Bolin Ding; Xiening Dai; Lu Lu; Jingren Zhou; |
| 88 | HierCDF: A Bayesian Network-based Hierarchical Cognitive Diagnosis Framework Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address these limitations, we propose a novel Bayesian network-based Hierarchical Cognitive Diagnosis Framework (HierCDF), which enables many traditional diagnostic models to flexibly integrate the attribute hierarchy for better diagnosis. |
Jiatong Li; Fei Wang; Qi Liu; Mengxiao Zhu; Wei Huang; Zhenya Huang; Enhong Chen; Yu Su; Shijin Wang; |
| 89 | Communication-Efficient Robust Federated Learning with Noisy Labels Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Training with corrupted labels is harmful to the federated learning task; however, little attention has been paid to FL in the case of label noise. In this paper, we focus on this problem and propose a learning-based reweighting approach to mitigate the effect of noisy labels in FL. |
Junyi Li; Jian Pei; Heng Huang; |
| 90 | Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We need representations that carry both feature information and as mush correct structure information as possible and are insensitive to structural perturbations. To this end, we propose an unsupervised pipeline, named STABLE, to optimize the graph structure. |
Kuan Li; Yang Liu; Xiang Ao; Jianfeng Chi; Jinghua Feng; Hao Yang; Qing He; |
| 91 | Mining Spatio-Temporal Relations Via Self-Paced Graph Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Unlike spatio-temporal GNNs focusing on designing complex architectures, we propose a novel adaptive graph construction strategy: Self-Paced Graph Contrastive Learning (SPGCL). |
Rongfan Li; Ting Zhong; Xinke Jiang; Goce Trajcevski; Jin Wu; Fan Zhou; |
| 92 | PAC-Wrap: Semi-Supervised PAC Anomaly Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Given their safety-criticality, these applications benefit from provable bounds on various errors in anomaly detection. To achieve this goal in the semi-supervised setting, we propose to provide Probably Approximately Correct (PAC) guarantees on the false negative and false positive detection rates for anomaly detection algorithms. |
Shuo Li; Xiayan Ji; Edgar Dobriban; Oleg Sokolsky; Insup Lee; |
| 93 | TransBO: Hyperparameter Optimization Via Two-Phase Transfer Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose TransBO, a novel two-phase transfer learning framework for HPO, which can deal with the complementary nature among source tasks and dynamics during knowledge aggregation issues simultaneously. |
Yang Li; Yu Shen; Huaijun Jiang; Wentao Zhang; Zhi Yang; Ce Zhang; Bin Cui; |
| 94 | Transfer Learning Based Search Space Design for Hyperparameter Tuning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we introduce an automatic method to design the BO search space with the aid of tuning history from past tasks. |
Yang Li; Yu Shen; Huaijun Jiang; Tianyi Bai; Wentao Zhang; Ce Zhang; Bin Cui; |
| 95 | Sparse Conditional Hidden Markov Model for Weakly Supervised Named Entity Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, evaluating the LFs is challenging due to the lack of ground truths. To address this issue, we propose the sparse conditional hidden Markov model (Sparse-CHMM). |
Yinghao Li; Le Song; Chao Zhang; |
| 96 | Graph Structural Attack By Perturbing Spectral Distance Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, an effective graph structural attack is investigated to disrupt graph spectral filters in the Fourier domain, which are the theoretical foundation of GCNs. |
Lu Lin; Ethan Blaser; Hongning Wang; |
| 97 | Deep Representations for Time-varying Brain Datasets Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper builds an efficient graph neural network model that incorporates both region-mapped fMRI sequences and structural connectivities obtained from DWI (diffusion-weighted imaging) as inputs. |
Sikun Lin; Shuyun Tang; Scott T. Grafton; Ambuj K. Singh; |
| 98 | Source Localization of Graph Diffusion Via Variational Autoencoders for Graph Inverse Problems Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To solve the above challenges, this paper presents a generic framework: Source Localization Variational AutoEncoder (SL-VAE) for locating the diffusion sources under arbitrary diffusion patterns. |
Chen Ling; Junji Jiang; Junxiang Wang; Zhao Liang; |
| 99 | Semantic Enhanced Text-to-SQL Parsing Via Iteratively Learning Schema Linking Graph Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a framework named ISESL-SQL to iteratively build a semantic enhanced schema-linking graph between question tokens and database schemas. |
Aiwei Liu; Xuming Hu; Li Lin; Lijie Wen; |
| 100 | Partial-Quasi-Newton Methods: Efficient Algorithms for Minimax Optimization Problems with Unbalanced Dimensionality Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a novel second-order optimization algorithm, called Partial-Quasi-Newton (PQN) method, which takes the advantage of unbalanced structure in the problem to establish the Hessian estimate efficiently. |
Chengchang Liu; Shuxian Bi; Luo Luo; John C.S. Lui; |
| 101 | MSDR: Multi-Step Dependency Relation Networks for Spatial Temporal Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we argue that it is insufficient to capture the long-range spatial dependencies from the implicit representations learned by temporal extracting modules. |
Dachuan Liu; Jin Wang; Shuo Shang; Peng Han; |
| 102 | User-Event Graph Embedding Learning for Context-Aware Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, an embedding layer with random initialization often suffers in practice from the sparsity of the contextual features, as well as the interactions between the users (or items) and context. In this paper, we propose a novel user-event graph embedding learning (UEG-EL) framework to address these two sparsity challenges. |
Dugang Liu; Mingkai He; Jinwei Luo; Jiangxu Lin; Meng Wang; Xiaolian Zhang; Weike Pan; Zhong Ming; |
| 103 | Graph-in-Graph Network for Automatic Gene Ontology Description Generation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel task: GO term description generation. |
Fenglin Liu; Bang Yang; Chenyu You; Xian Wu; Shen Ge; Adelaide Woicik; Sheng Wang; |
| 104 | Graph Rationalization with Environment-based Augmentations Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we introduce a new augmentation operation called environment replacement that automatically creates virtual data examples to improve rationale identification. |
Gang Liu; Tong Zhao; Jiaxin Xu; Tengfei Luo; Meng Jiang; |
| 105 | Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel label-enhanced prototypical network (LPN) for multi-label few-shot aspect category detection. |
Han Liu; Feng Zhang; Xiaotong Zhang; Siyang Zhao; Junjie Sun; Hong Yu; Xianchao Zhang; |
| 106 | Fair Representation Learning: An Alternative to Mutual Information Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we introduce distance covariance as a new dependence measure into fair representation learning. |
Ji Liu; Zenan Li; Yuan Yao; Feng Xu; Xiaoxing Ma; Miao Xu; Hanghang Tong; |
| 107 | Joint Knowledge Graph Completion and Question Answering Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a neural model named BiNet to jointly handle KGC and multi-hop KGQA, and formulate it as a multi-task learning problem. |
Lihui Liu; Boxin Du; Jiejun Xu; Yinglong Xia; Hanghang Tong; |
| 108 | RL2: A Call for Simultaneous Representation Learning and Rule Learning for Graph Streams Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The goal of this paper is to show that it is feasible to simultaneously and efficiently perform representation learning (for connectionist networks) and rule learning spontaneously out of the same online training process for graph streams. |
Qu Liu; Tingjian Ge; |
| 109 | Mask and Reason: Pre-Training Knowledge Graph Transformers for Complex Logical Queries Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we present the Knowledge Graph Transformer (kgTransformer) with masked pre-training and fine-tuning strategies. |
Xiao Liu; Shiyu Zhao; Kai Su; Yukuo Cen; Jiezhong Qiu; Mengdi Zhang; Wei Wu; Yuxiao Dong; Jie Tang; |
| 110 | UD-GNN: Uncertainty-aware Debiased Training on Semi-Homophilous Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To mitigate the bias issue, we explore an Uncertainty-aware Debiasing (UD) framework, which retains the knowledge of the biased model on certain nodes and compensates for the nodes with high uncertainty. |
Yang Liu; Xiang Ao; Fuli Feng; Qing He; |
| 111 | Practical Counterfactual Policy Learning for Top-K Recommendations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This work studies policy learning approaches for top-K recommendations with a large item space and points out several difficulties related to importance weight explosion, observation insufficiency, and training efficiency. |
Yaxu Liu; Jui-Nan Yen; Bowen Yuan; Rundong Shi; Peng Yan; Chih-Jen Lin; |
| 112 | Geometer: Graph Few-Shot Class-Incremental Learning Via Prototype Representation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Novel classes appear incrementally along with few labeling due to its newly emergence or lack of exploration. In this paper, we focus on this challenging but practical graph few-shot class-incremental learning (GFSCIL) problem and propose a novel method called Geometer. |
Bin Lu; Xiaoying Gan; Lina Yang; Weinan Zhang; Luoyi Fu; Xinbing Wang; |
| 113 | Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, the spatio-temporal graphs among different cities show irregular structures and varied features, which limits the feasibility of existing Few-Shot Learning (FSL) methods. Therefore, we propose a model-agnostic few-shot learning framework for spatio-temporal graph called ST-GFSL. |
Bin Lu; Xiaoying Gan; Weinan Zhang; Huaxiu Yao; Luoyi Fu; Xinbing Wang; |
| 114 | Matrix Profile XXIV: Scaling Time Series Anomaly Detection to Trillions of Datapoints and Ultra-fast Arriving Data Streams Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: First, they are limited to the batch case, whereas the online case is more actionable. Second, these algorithms exhibit poor scalability beyond tens of thousands of datapoints. In this work we introduce DAMP, a novel algorithm that addresses both these issues. |
Yue Lu; Renjie Wu; Abdullah Mueen; Maria A. Zuluaga; Eamonn Keogh; |
| 115 | S2RL: Do We Really Need to Perceive All States in Deep Multi-Agent Reinforcement Learning? Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, we propose a sparse state based MARL (S2RL) framework, which utilizes a sparse attention mechanism to discard irrelevant information in local observations. |
Shuang Luo; Yinchuan Li; Jiahui Li; Kun Kuang; Furui Liu; Yunfeng Shao; Chao Wu; |
| 116 | Learning Differential Operators for Interpretable Time Series Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose an learning framework that can automatically obtain interpretable PDE models from sequential data. |
Yingtao Luo; Chang Xu; Yang Liu; Weiqing Liu; Shun Zheng; Jiang Bian; |
| 117 | Learning Causal Effects on Hypergraphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Specifically, in this paper, we focus on the problem of individual treatment effect (ITE) estimation on hypergraphs, aiming to estimate how much an intervention (e.g., wearing face covering) would causally affect an outcome (e.g., COVID-19 infection) of each individual node. |
Jing Ma; Mengting Wan; Longqi Yang; Jundong Li; Brent Hecht; Jaime Teevan; |
| 118 | ML4S: Learning Causal Skeleton from Vicinal Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Our proposed framework, ML4S, adopts order-based cascade classifiers and pruning strategies that can withstand high computational overhead without sacrificing accuracy. |
Pingchuan Ma; Rui Ding; Haoyue Dai; Yuanyuan Jiang; Shuai Wang; Shi Han; Dongmei Zhang; |
| 119 | Non-stationary Time-aware Kernelized Attention for Temporal Event Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a non-stationary time-aware kernelized attention approach for input sequences of neural networks. |
Yu Ma; Zhining Liu; Chenyi Zhuang; Yize Tan; Yi Dong; Wenliang Zhong; Jinjie Gu; |
| 120 | CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose to model the cooperative association between the two different views through cross-view contrastive learning. |
Yunshan Ma; Yingzhi He; An Zhang; Xiang Wang; Tat-Seng Chua; |
| 121 | Discovering Invariant and Changing Mechanisms from Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To discover invariant and changing mechanisms from data, we propose extending the algorithmic model for causation to mechanism changes and instantiating it using Minimum Description Length. |
Sarah Mameche; David Kaltenpoth; Jilles Vreeken; |
| 122 | Learning Models of Individual Behavior in Chess Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Existing work has focused on capturing human behavior in an aggregate sense, which potentially limits the benefit any particular individual could gain from interaction with these systems. We extend this line of work by developing highly accurate predictive models of individual human behavior in chess. |
Reid McIlroy-Young; Russell Wang; Siddhartha Sen; Jon Kleinberg; Ashton Anderson; |
| 123 | Minimizing Congestion for Balanced Dominators Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Recent work leverages the sparsity of the assembly graph to find r-dominating sets which enable rapid approximate queries through a dominator-centric graph partition. In this paper, we consider two problems related to reducing uncertainty and improving scalability in this setting. |
Yosuke Mizutani; Annie Staker; Blair D. Sullivan; |
| 124 | Extracting Relevant Information from User’s Utterances in Conversational Search and Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a model based on reinforcement learning, namely RelInCo, which takes the user’s utterances and the context of the conversation and classifies each word in the user’s utterances as belonging to the relevant or non-relevant class. |
Ali Montazeralghaem; James Allan; |
| 125 | Nonlinearity Encoding for Extrapolation of Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose automated nonlinearity encoder (ANE) that is a data-agnostic embedding method to improve the extrapolation capabilities of neural networks by conversely linearizing the original input-to-target relationships without architectural modifications of prediction models. |
Gyoung S. Na; Chanyoung Park; |
| 126 | Learning Fair Representation Via Distributional Contrastive Disentanglement Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose a new approach, learningFAir Representation via distributional CONtrastive Variational AutoEncoder (FarconVAE), which induces the latent space to be disentangled into sensitive and non-sensitive parts. |
Changdae Oh; Heeji Won; Junhyuk So; Taero Kim; Yewon Kim; Hosik Choi; Kyungwoo Song; |
| 127 | Predicting Opinion Dynamics Via Sociologically-Informed Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we present the first hybrid method called Sociologically-Informed Neural Network (SINN), which integrates theoretical models and social media data by transporting the concepts of physics-informed neural networks (PINNs) from natural science (i.e., physics) into social science (i.e., sociology and social psychology). |
Maya Okawa; Tomoharu Iwata; |
| 128 | FedWalk: Communication Efficient Federated Unsupervised Node Embedding with Differential Privacy Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we introduce FedWalk, a random-walk-based unsupervised node embedding algorithm that operates in such a node-level visibility graph with raw graph information remaining locally. |
Qiying Pan; Yifei Zhu; |
| 129 | MetaV: A Meta-Verifier Approach to Task-Agnostic Model Fingerprinting Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, these methods heavily rely on the characteristics of classification tasks which inhibits their application to more general scenarios. To address this issue, we present MetaV, the first task-agnostic model fingerprinting framework which enables fingerprinting on a much wider range of DNNs independent from the downstream learning task, and exhibits strong robustness against a variety of ownership obfuscation techniques. |
Xudong Pan; Yifan Yan; Mi Zhang; Min Yang; |
| 130 | Core-periphery Models for Hypergraphs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We introduce a random hypergraph model for core-periphery structure. |
Marios Papachristou; Jon Kleinberg; |
| 131 | Compute Like Humans: Interpretable Step-by-step Symbolic Computation with Deep Neural Network Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we argue that any complex symbolic computation can be broken down to a sequence of finite Fundamental Computation Transformations (FCT), which are grounded as certain mathematical expression computation transformations. |
Shuai Peng; Di Fu; Yong Cao; Yijun Liang; Gu Xu; Liangcai Gao; Zhi Tang; |
| 132 | Bilateral Dependency Optimization: Defending Against Model-inversion Attacks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we aim to minimize the dependency between the latent representations and the inputs while maximizing the dependency between latent representations and the outputs, named a bilateral dependency optimization (BiDO) strategy. |
Xiong Peng; Feng Liu; Jingfeng Zhang; Long Lan; Junjie Ye; Tongliang Liu; Bo Han; |
| 133 | Evaluating Knowledge Graph Accuracy Powered By Optimized Human-machine Collaboration Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Motivated by the fact that the major advance of machines is the strong computing power while humans are skilled in correctness verification, we propose an efficient interactive method to reduce the overall cost for evaluating the KG quality, which produces accuracy estimates with a statistical guarantee for both triples and entities. |
Yifan Qi; Weiguo Zheng; Liang Hong; Lei Zou; |
| 134 | Neural Bandit with Arm Group Graph Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Motivated by the fact that the arms usually exhibit group behaviors and the mutual impacts exist among groups, we introduce a new model, Arm Group Graph (AGG), where the nodes represent the groups of arms and the weighted edges formulate the correlations among groups. |
Yunzhe Qi; Yikun Ban; Jingrui He; |
| 135 | Rep2Vec: Repository Embedding Via Heterogeneous Graph Adversarial Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In addition, they usually require a mass of resources to obtain sufficient labeled data for model training while ignoring the usefully handy unlabeled data. To this end, we propose a novel model Rep2Vec which integrates the code content, the structural relations, and the unlabeled data to learn the repository representations. |
Yiyue Qian; Yiming Zhang; Qianlong Wen; Yanfang Ye; Chuxu Zhang; |
| 136 | External Knowledge Infusion for Tabular Pre-training Models with Dual-adapters Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, we propose the dual-adapters inserted within the pre-trained tabular model for flexible and efficient knowledge injection. |
Can Qin; Sungchul Kim; Handong Zhao; Tong Yu; Ryan A. Rossi; Yun Fu; |
| 137 | Releasing Private Data for Numerical Queries Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a new mechanism to privatize a dataset D for a given set Q of numerical queries, achieving an error of Õ (?n • ?w(D)) for each query w ? Q, where ?w(D) is the maximum contribution of any tuple in D queried by w. |
Yuan Qiu; Wei Dong; Ke Yi; Bin Wu; Feifei Li; |
| 138 | Importance Prioritized Policy Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Based on the analysis, we propose an importance prioritized PD framework that highlights the training on important frames, so as to learn efficiently. |
Xinghua Qu; Yew Soon Ong; Abhishek Gupta; Pengfei Wei; Zhu Sun; Zejun Ma; |
| 139 | Synthesising Audio Adversarial Examples for Automatic Speech Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: For the first time, we propose the Speech Synthesising based Attack (SSA), a novel threat model that constructs audio adversarial examples entirely from scratch, i.e., without depending on any existing audio to fool cutting-edge ASR models. To this end, we introduce a conditional variational auto-encoder (CVAE) as the speech synthesiser. |
Xinghua Qu; Pengfei Wei; Mingyong Gao; Zhu Sun; Yew Soon Ong; Zejun Ma; |
| 140 | P-Meta: Towards On-device Deep Model Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, we propose p-Meta, a new meta learning method that enforces structure-wise partial parameter updates while ensuring fast generalization to unseen tasks. |
Zhongnan Qu; Zimu Zhou; Yongxin Tong; Lothar Thiele; |
| 141 | Fair and Interpretable Models for Survival Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose novel fair and interpretable survival models which use pseudo valued-based objective functions with fairness definitions as constraints for predicting subject-specific survival probabilities. |
Md Mahmudur Rahman; Sanjay Purushotham; |
| 142 | Graph-Flashback Network for Next Location Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To incorporate the learned graph into sequential model, we propose a novel network Graph-Flashback for recommendation. |
Xuan Rao; Lisi Chen; Yong Liu; Shuo Shang; Bin Yao; Peng Han; |
| 143 | SMORE: Knowledge Graph Completion and Multi-hop Reasoning in Massive Knowledge Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Here we present Scalable Multi-hOp REasoning (SMORE), the first general framework for both single-hop and multi-hop reasoning in KGs. |
Hongyu Ren; Hanjun Dai; Bo Dai; Xinyun Chen; Denny Zhou; Jure Leskovec; Dale Schuurmans; |
| 144 | DICE: Domain-attack Invariant Causal Learning for Improved Data Privacy Protection and Adversarial Robustness Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Based on DICM, we propose a coherent causal invariant principle, which guides our algorithm design to infer the human-like causal relations. |
Qibing Ren; Yiting Chen; Yichuan Mo; Qitian Wu; Junchi Yan; |
| 145 | Variational Flow Graphical Model Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper introduces a novel approach embedding flow-based models in hierarchical structures. |
Shaogang Ren; Belhal Karimi; Dingcheng Li; Ping Li; |
| 146 | Semi-supervised Drifted Stream Learning with Short Lookback Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: SDSL imposes two under-addressed challenges on existing methods in semi-supervised learning and continuous learning: 1) robust pseudo-labeling under gradual shifts and 2) anti-forgetting adaptation with short lookback. To tackle these challenges, we propose a principled and generic generation-replay framework to solve SDSL. |
Weijieying Ren; Pengyang Wang; Xiaolin Li; Charles E. Hughes; Yanjie Fu; |
| 147 | Fair Ranking As Fair Division: Impact-Based Individual Fairness in Ranking Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Our axioms of envy-freeness and dominance over uniform ranking postulate that for a fair ranking policy every item should prefer their own rank allocation over that of any other item, and that no item should be actively disadvantaged by the rankings. To compute ranking policies that are fair according to these axioms, we propose a new ranking objective related to the Nash Social Welfare. |
Yuta Saito; Thorsten Joachims; |
| 148 | A Generalized Backward Compatibility Metric Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we first analyze the existing backward compatibility metrics and reveal that these metrics essentially assess the same quantity between old and new models. In addition, to obtain a unified view of backward compatibility metrics, we propose a generalized backward compatibility (GBC) metric that can represent the existing backward compatibility metrics. |
Tomoya Sakai; |
| 149 | Balancing Bias and Variance for Active Weakly Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose to conduct novel active deep multiple instance learning that samples a small subset of informative instances for annotation, aiming to significantly boost the instance-level prediction. |
Hitesh Sapkota; Qi Yu; |
| 150 | On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The propensity model introduced by Jain et al has become a standard approach for dealing with missing and long-tail labels in extreme multi-label classification (XMLC). In this paper, we critically revise this approach showing that despite its theoretical soundness, its application in contemporary XMLC works is debatable. |
Erik Schultheis; Marek Wydmuch; Rohit Babbar; Krzysztof Dembczynski; |
| 151 | Active Model Adaptation Under Unknown Shift Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To cope with such a novel problem Resource Constrained Adaptation under Unknown Shift, in this paper we study active model adaptation both theoretically and empirically. |
Jie-Jing Shao; Yunlu Xu; Zhanzhan Cheng; Yu-Feng Li; |
| 152 | Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, the patterns of time series and the dependencies between them (i.e., the temporal and spatial patterns) need to be analyzed based on long-term historical MTS data. To address this issue, we propose a novel framework, in which STGNN is Enhanced by a scalable time series Pre-training model (STEP). |
Zezhi Shao; Zhao Zhang; Fei Wang; Yongjun Xu; |
| 153 | Multi-View Clustering for Open Knowledge Base Canonicalization Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose CMVC, a novel unsupervised framework that leverages these two views of knowledge jointly for canonicalizing OKBs without the need of manually annotated labels. To achieve this goal, we pro- pose a multi-view CH K-Means clustering algorithm to mutually reinforce the clustering of view-specific embeddings learned from each view by considering their different clustering qualities. |
Wei Shen; Yang Yang; Yinan Liu; |
| 154 | Deep Learning for Prognosis Using Task-fMRI: A Novel Architecture and Training Scheme Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a deep multi-model architecture to encode multi-view brain activities from t-fMRI data and a multi-layer perceptron ensemble model to combine these view models and make subject-wise predictions. |
Ge Shi; Jason Smucny; Ian Davidson; |
| 155 | Pairwise Adversarial Training for Unsupervised Class-imbalanced Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a pairwise adversarial training approach for class-imbalanced domain adaptation. |
Weili Shi; Ronghang Zhu; Sheng Li; |
| 156 | State Dependent Parallel Neural Hawkes Process for Limit Order Book Event Stream Prediction and Simulation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Following recent successes in the literature that combine stochastic point processes with neural networks to model event stream patterns, we propose a novel state-dependent parallel neural Hawkes process to predict LOB events and simulate realistic LOB data. |
Zijian Shi; John Cartlidge; |
| 157 | Robust and Informative Text Augmentation (RITA) Via Constrained Worst-Case Transformations for Low-Resource Named Entity Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, deep learning models often require a large amount of annotated data to achieve satisfactory performance, and NER annotation is significantly time-consuming and labor-intensive due to the fine-grained labels. To address this issue, we propose a textual data augmentation method that can automatically generate informative synthetic samples, which contribute to the development of a robust classifier. |
Hyunwoo Sohn; Baekkwan Park; |
| 158 | GUIDE: Group Equality Informed Individual Fairness in Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This leads to drastically different levels of individual fairness among groups. We tackle this problem by proposing a novel GNN framework GUIDE to achieve group equality informed individual fairness in GNNs. |
Weihao Song; Yushun Dong; Ninghao Liu; Jundong Li; |
| 159 | Learning on Graphs with Out-of-Distribution Nodes Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we define the problem of graph learning with out-of-distribution nodes. |
Yu Song; Donglin Wang; |
| 160 | RGVisNet: A Hybrid Retrieval-Generation Neural Framework Towards Automatic Data Visualization Generation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Inspired by how developers reuse previously validated source code snippets from code search engines or a large-scale codebase when they conduct software development, we provide a novel hybrid retrieval-generation framework named RGVisNet for text-to-vis. |
Yuanfeng Song; Xuefang Zhao; Raymond Chi-Wing Wong; Di Jiang; |
| 161 | Towards An Optimal Asymmetric Graph Structure for Robust Semi-supervised Node Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we give a precise definition on the optimality of the refined graph and provide the exact form of an optimal asymmetric graph structure designed explicitly for the semi-supervised node classification by distinguishing the different roles of labeled and unlabeled nodes through theoretical analysis. |
Zixing Song; Yifei Zhang; Irwin King; |
| 162 | ERNet: Unsupervised Collective Extraction and Registration in Neuroimaging Data Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we study the problem of unsupervised collective extraction and registration in neuroimaging data. |
Yao Su; Zhentian Qian; Lifang He; Xiangnan Kong; |
| 163 | Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a hypergraph neural network based model named HIRS. |
Yixin Su; Yunxiang Zhao; Sarah Erfani; Junhao Gan; Rui Zhang; |
| 164 | Knowledge Enhanced Search Result Diversification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Given that the knowledge base can offer well-defined entities and explicit relationships between entities, we exploit knowledge to model the relationship between documents and the query and propose a knowledge-enhanced search result diversification approach KEDIV. |
Zhan Su; Zhicheng Dou; Yutao Zhu; Ji-Rong Wen; |
| 165 | Causal Attention for Interpretable and Generalizable Graph Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we take a causal look at the GNN modeling for graph classification. |
Yongduo Sui; Xiang Wang; Jiancan Wu; Min Lin; Xiangnan He; Tat-Seng Chua; |
| 166 | Demystify Hyperparameters for Stochastic Optimization with Transferable Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we give a unified analysis of several popular optimizers, e.g., Polyak’s heavy ball momentum and Nesterov’s accelerated gradient. |
Jianhui Sun; Mengdi Huai; Kishlay Jha; Aidong Zhang; |
| 167 | GPPT: Graph Pre-training and Prompt Tuning to Generalize Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Based on the pre-trained model, we propose the graph prompting function to modify the standalone node into a token pair, and reformulate the downstream node classification looking the same as edge prediction. |
Mingchen Sun; Kaixiong Zhou; Xin He; Ying Wang; Xin Wang; |
| 168 | PureGAM: Learning An Inherently Pure Additive Model Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose pureGAM, an inherently pure additive model of both main effects and higher-order interactions. |
Xingzhi Sun; Ziyu Wang; Rui Ding; Shi Han; Dongmei Zhang; |
| 169 | Learning Optimal Priors for Task-Invariant Representations in Variational Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this study, we theoretically investigate why the CVAE cannot sufficiently reduce the task-dependency and show that the simple standard Gaussian prior is one of the causes. |
Hiroshi Takahashi; Tomoharu Iwata; Atsutoshi Kumagai; Sekitoshi Kanai; Masanori Yamada; Yuuki Yamanaka; Hisashi Kashima; |
| 170 | Clustering with Fair-Center Representation: Parameterized Approximation Algorithms and Heuristics Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study a variant of classical clustering formulations in the context of algorithmic fairness, known as diversity-aware clustering. |
Suhas Thejaswi; Ameet Gadekar; Bruno Ordozgoiti; Michal Osadnik; |
| 171 | Incremental Cognitive Diagnosis for Intelligent Education Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, we propose a novel framework, Incremental Cognitive Diagnosis (ICD), to tailor cognitive diagnosis into the online scenario of intelligent education. |
Shiwei Tong; Jiayu Liu; Yuting Hong; Zhenya Huang; Le Wu; Qi Liu; Wei Huang; Enhong Chen; Dan Zhang; |
| 172 | Improving Data-driven Heterogeneous Treatment Effect Estimation Under Structure Uncertainty Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: At the same time, accounting for the causal structure of real-world data is rarely trivial since the causal mechanisms that gave rise to the data are typically unknown. To address this problem, we develop a feature selection method that considers each feature’s value for HTE estimation and learns the relevant parts of the causal structure from data. |
Christopher Tran; Elena Zheleva; |
| 173 | Aligning Dual Disentangled User Representations from Ratings and Textual Content Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To further improve not only the effectiveness of recommendations but also the interpretability of the representations, we propose to learn a second set of disentangled user representations from textual content and to align the two sets of representations with one another. |
Nhu-Thuat Tran; Hady W. Lauw; |
| 174 | Dense Feature Tracking of Atmospheric Winds with Deep Optical Flow Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This work presents WindFlow as the first machine learning based system for feature tracking atmospheric motion using optical flow. |
Thomas J. Vandal; Kate Duffy; Will McCarty; Akira Sewnath; Ramakrishna Nemani; |
| 175 | Towards Representation Alignment and Uniformity in Collaborative Filtering Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we measure the representation quality in CF from the perspective of alignment and uniformity on the hypersphere. |
Chenyang Wang; Yuanqing Yu; Weizhi Ma; Min Zhang; Chong Chen; Yiqun Liu; Shaoping Ma; |
| 176 | Group-wise Reinforcement Feature Generation for Optimal and Explainable Representation Space Reconstruction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Can we simultaneously address the automation, explicitness, and optimal challenges in representation space reconstruction for a machine learning task? To answer this question, we propose a group-wise reinforcement generation perspective. |
Dongjie Wang; Yanjie Fu; Kunpeng Liu; Xiaolin Li; Yan Solihin; |
| 177 | A Model-Agnostic Approach to Differentially Private Topic Mining Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To our best knowledge, we propose the first differentially private topic mining technique (namely TopicDP) which injects well-calibrated Gaussian noise into the matrix output of any topic mining algorithm to ensure differential privacy and good utility. |
Han Wang; Jayashree Sharma; Shuya Feng; Kai Shu; Yuan Hong; |
| 178 | Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, motivated by a proliferation of options of alignment regularizations, we seek to evaluate the performances of several popular design choices along the dimensions of robustness and invariance, for which we introduce a new test procedure. |
Haohan Wang; Zeyi Huang; Xindi Wu; Eric Xing; |
| 179 | Estimating Individualized Causal Effect with Confounded Instruments Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we focus on estimating the ICE with confounded instruments that violate the unconfounded instruments assumption. |
Haotian Wang; Wenjing Yang; Longqi Yang; Anpeng Wu; Liyang Xu; Jing Ren; Fei Wu; Kun Kuang; |
| 180 | Make Fairness More Fair: Fair Item Utility Estimation and Exposure Re-Distribution Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose the concept of items’ fair utility, defined as the proportion of users who are interested in the item among all users. |
Jiayin Wang; Weizhi Ma; Jiayu Li; Hongyu Lu; Min Zhang; Biao Li; Yiqun Liu; Peng Jiang; Shaoping Ma; |
| 181 | Streaming Graph Neural Networks with Generative Replay Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a streaming GNN based on generative replay, which can incrementally learn new patterns while maintaining existing knowledge without accessing historical data. |
Junshan Wang; Wenhao Zhu; Guojie Song; Liang Wang; |
| 182 | Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose a novel framework to elicit relational structures from large-scale pre-trained language models (PLMs) via a probing procedure based on Poincaré distance metric, and use the induced relations to augment current graph-based parsers for better schema linking. |
Lihan Wang; Bowen Qin; Binyuan Hui; Bowen Li; Min Yang; Bailin Wang; Binhua Li; Jian Sun; Fei Huang; Luo Si; Yongbin Li; |
| 183 | Stabilizing Voltage in Power Distribution Networks Via Multi-Agent Reinforcement Learning with Transformer Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we introduce the transformer architecture to extract representations adapting to power network problems and propose a Transformer-based Multi-Agent Actor-Critic framework (T-MAAC) to stabilize voltage in power distribution networks. |
Minrui Wang; Mingxiao Feng; Wengang Zhou; Houqiang Li; |
| 184 | Task-Adaptive Few-shot Node Classification Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Therefore, to effectively alleviate the impact of task variance, we propose a task-adaptive node classification framework under the few-shot learning setting. |
Song Wang; Kaize Ding; Chuxu Zhang; Chen Chen; Jundong Li; |
| 185 | Partial Label Learning with Discrimination Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Nevertheless, the feature representations of partial label training examples may be less informative of the ground-truth labels, which may result in negative influences on the disambiguation process. To circumvent this difficulty, the first attempt towards discrimination augmentation for partial label learning is investigated in this paper. |
Wei Wang; Min-Ling Zhang; |
| 186 | Towards Unified Conversational Recommender Systems Via Knowledge-Enhanced Prompt Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, these approaches still rely on different architectures or techniques to develop the two modules, making it difficult for effective module integration. To address this problem, we propose a unified CRS model named UniCRS based on knowledge-enhanced prompt learning. |
Xiaolei Wang; Kun Zhou; Ji-Rong Wen; Wayne Xin Zhao; |
| 187 | Improving Fairness in Graph Neural Networks Via Mitigating Sensitive Attribute Leakage Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Motivated by our analysis, we propose Fair View Graph Neural Network (FairVGNN) to generate fair views of features by automatically identifying and masking sensitive-correlated features considering correlation variation after feature propagation. |
Yu Wang; Yuying Zhao; Yushun Dong; Huiyuan Chen; Jundong Li; Tyler Derr; |
| 188 | Graph Neural Networks with Node-wise Architecture Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Nevertheless, node-wise architecture cannot be realized by trivially applying NAS methods node by node due to the scalability issue and the need for determining test nodes’ architectures. To tackle these challenges, we propose a framework wherein the parametric controllers decide the GNN architecture for each node based on its local patterns. |
Zhen Wang; Zhewei Wei; Yaliang Li; Weirui Kuang; Bolin Ding; |
| 189 | Debiasing Learning for Membership Inference Attacks Against Recommender Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To address the above limitations, we propose a Debiasing Learning for Membership Inference Attacks against recommender systems (DL-MIA) framework that has four main components: (i) a difference vector generator, (ii) a disentangled encoder, (iii) a weight estimator, and (iv) an attack model. |
Zihan Wang; Na Huang; Fei Sun; Pengjie Ren; Zhumin Chen; Hengliang Luo; Maarten de Rijke; Zhaochun Ren; |
| 190 | Invariant Preference Learning for General Debiasing in Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we consider a more practical setting where we aim to conduct general debiasing with the biased observational data alone. |
Zimu Wang; Yue He; Jiashuo Liu; Wenchao Zou; Philip S. Yu; Peng Cui; |
| 191 | An Embedded Feature Selection Framework for Control Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, a novel framework, namely the Dual-world embedded Attentive Feature Selection (D-AFS), can efficiently select the most relevant sensors for the system under dynamic control. |
Jiawen Wei; Fangyuan Wang; Wanxin Zeng; Wenwei Lin; Ning Gui; |
| 192 | Comprehensive Fair Meta-learned Recommender System Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a comprehensive fair meta-learning framework, named CLOVER, for ensuring the fairness of meta-learned recommendation models. |
Tianxin Wei; Jingrui He; |
| 193 | SagDRE: Sequence-Aware Graph-Based Document-Level Relation Extraction with Adaptive Margin Loss Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose SagDRE model, which further considers and captures the original sequential information from the text. |
Ying Wei; Qi Li; |
| 194 | Disentangled Dynamic Heterogeneous Graph Learning for Opioid Overdose Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, we propose a novel model DDHGNN – Disentangled Dynamic Heterogeneous Graph Neural Network, for over-prescribing prediction. |
Qianlong Wen; Zhongyu Ouyang; Jianfei Zhang; Yiyue Qian; Yanfang Ye; Chuxu Zhang; |
| 195 | Beyond Point Prediction: Capturing Zero-Inflated & Heavy-Tailed Spatiotemporal Data with Deep Extreme Mixture Models Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To address these challenges, we propose Deep Extreme Mixture Model (DEMM), fusing a deep learning-based hurdle model with extreme value theory to enable point and distribution prediction of zero-inflated, heavy-tailed spatiotemporal variables. |
Tyler Wilson; Andrew McDonald; Asadullah Hill Galib; Pang-Ning Tan; Lifeng Luo; |
| 196 | Multi-fidelity Hierarchical Neural Processes Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose Multi-fidelity Hierarchical Neural Processes (MF-HNP), a unified neural latent variable model for multi-fidelity surrogate modeling. |
Dongxia Wu; Matteo Chinazzi; Alessandro Vespignani; Yi-An Ma; Rose Yu; |
| 197 | Domain Adaptation with Dynamic Open-Set Targets Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we focus on the more realistic open-set domain adaptation setting with a static source task and a time evolving target task where novel unknown target classes appear over time. |
Jun Wu; Jingrui He; |
| 198 | Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: For production deployment, we propose a dynamic gating unit to pre-determine the utility of an exploration. |
Kailun Wu; Weijie Bian; Zhangming Chan; Lejian Ren; Shiming Xiang; Shu-Guang Han; Hongbo Deng; Bo Zheng; |
| 199 | CLARE: A Semi-supervised Community Detection Algorithm Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To address these issues, we propose CLARE, which consists of two key components, Community Locator and Community Rewriter. |
Xixi Wu; Yun Xiong; Yao Zhang; Yizhu Jiao; Caihua Shan; Yiheng Sun; Yangyong Zhu; Philip S. Yu; |
| 200 | Geometric Policy Iteration for Markov Decision Processes Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Inspired by these geometric properties, we propose a new algorithm, Geometric Policy Iteration (GPI), to solve discounted MDPs. |
Yue Wu; Jesús A. De Loera; |
| 201 | Non-stationary A/B Tests Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: When the experiment design phase of an A/B test allows, we propose a new time-grouped randomization approach to make a better balance on treatment and control assignments in presence of time nonstationarity. |
Yuhang Wu; Zeyu Zheng; Guangyu Zhang; Zuohua Zhang; Chu Wang; |
| 202 | Robust Tensor Graph Convolutional Networks Via T-SVD Based Graph Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a Robust Tensor Graph Convolutional Network (RT-GCN) model to improve the robustness. |
Zhebin Wu; Lin Shu; Ziyue Xu; Yaomin Chang; Chuan Chen; Zibin Zheng; |
| 203 | Self-Supervised Hypergraph Transformer for Recommender Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose SHT, a novel Self-Supervised Hypergraph Transformer framework (SHT) which augments user representations by exploring the global collaborative relationships in an explicit way. |
Lianghao Xia; Chao Huang; Chuxu Zhang; |
| 204 | Sample-Efficient Kernel Mean Estimator with Marginalized Corrupted Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose to corrupt data examples with noise from known distributions and present a new kernel mean estimator, called the marginalized kernel mean estimator, which estimates kernel mean under the corrupted distributions. |
Xiaobo Xia; Shuo Shan; Mingming Gong; Nannan Wang; Fei Gao; Haikun Wei; Tongliang Liu; |
| 205 | RetroGraph: Retrosynthetic Planning with Graph Search Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose a graph-based search policy that eliminates the redundant explorations of any intermediate molecules. |
Shufang Xie; Rui Yan; Peng Han; Yingce Xia; Lijun Wu; Chenjuan Guo; Bin Yang; Tao Qin; |
| 206 | Ultrahyperbolic Knowledge Graph Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To capture the topological heterogeneity of KGs, we present an ultrahyperbolic KG embedding (UltraE) in an ultrahyperbolic (or pseudo-Riemannian) manifold that seamlessly interleaves hyperbolic and spherical manifolds. |
Bo Xiong; Shichao Zhu; Mojtaba Nayyeri; Chengjin Xu; Shirui Pan; Chuan Zhou; Steffen Staab; |
| 207 | End-to-End Semi-Supervised Ordinal Regression AUC Maximization with Convolutional Kernel Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Although recent research works have shown that directly optimizing AUC can impose a better ranking on the data than optimizing traditional error rate, it is still an open question to design an efficient semi-supervised ordinal regression AUC maximization algorithm based on CKN with convergence guarantee. To address this question, in this paper, we propose a new semi-supervised ordinal regression CKN algorithm (S^2 CKNOR) with end-to-end AUC maximization. |
Ziran Xiong; Wanli Shi; Bin Gu; |
| 208 | MetaPTP: An Adaptive Meta-optimized Model for Personalized Spatial Trajectory Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, we propose an adaptive meta-optimized model called MetaPTP for personalized spatial trajectory prediction. |
Yuan Xu; Jiajie Xu; Jing Zhao; Kai Zheng; An Liu; Lei Zhao; Xiaofang Zhou; |
| 209 | Towards A Native Quantum Paradigm for Graph Representation Learning: A Sampling-based Recurrent Embedding Approach Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Different from many existing classical-quantum hybrid machine learning models on graphs, in this paper we take a more aggressive initiative for developing a native quantum paradigm for (attributed) graph representation learning, which to our best knowledge, has not been fulfilled in literature yet. |
Ge Yan; Yehui Tang; Junchi Yan; |
| 210 | Solving The Batch Stochastic Bin Packing Problem in Cloud: A Chance-constrained Optimization Approach Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper investigates a critical resource allocation problem in the first party cloud: scheduling containers to machines. |
Jie Yan; Yunlei Lu; Liting Chen; Si Qin; Yixin Fang; Qingwei Lin; Thomas Moscibroda; Saravan Rajmohan; Dongmei Zhang; |
| 211 | On-Device Learning for Model Personalization with Large-Scale Cloud-Coordinated Domain Adaption Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a new device-cloud collaborative learning framework under the paradigm of domain adaption, called MPDA, to break the dilemmas of purely cloud-based learning and on-device training. |
Yikai Yan; Chaoyue Niu; Renjie Gu; Fan Wu; Shaojie Tang; Lifeng Hua; Chengfei Lyu; Guihai Chen; |
| 212 | Enhancing Machine Learning Approaches for Graph Optimization Problems with Diversifying Graph Augmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address this critical issue, in this paper, we propose a new framework, named Learning with Iterative Graph Diversification (LIGD), and formulate a new research problem, named Diverse Graph Modification Problem (DGMP), that iteratively generate diversified training graphs and train the models that solve graph optimization problems to significantly improve their performance. |
Chen-Hsu Yang; Chih-Ya Shen; |
| 213 | Causal Discovery on Non-Euclidean Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We start by proposing the Non-Euclidean Causal Model (NECM) which describes the causal generative relationship of non-Euclidean data and creates a new tensor data type along with a mapping process for the non-Euclidean causal mechanism. |
Jing Yang; Kai Xie; Ning An; |
| 214 | HICF: Hyperbolic Informative Collaborative Filtering Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Nonetheless, it remains unclear which kinds of items can be effectively recommended by the hyperbolic model and which cannot. To address the above concerns, we take the most basic recommendation technique, collaborative filtering, as a medium, to investigate the behaviors of hyperbolic and Euclidean recommendation models. |
Menglin Yang; Zhihao Li; Min Zhou; Jiahong Liu; Irwin King; |
| 215 | Toward Real-life Dialogue State Tracking Involving Negative Feedback Utterances Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Thus, in this paper, we will explore the role of negative feedback utterances in dialogue state tracking in detail through simulated negative feedback utterances. |
Puhai Yang; Heyan Huang; Wei Wei; Xian-Ling Mao; |
| 216 | Numerical Tuple Extraction from Tables with Pre-training Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To represent cells with their intricate correlations in tables, we propose a BERT-based pre-trained language model, TableLM, to encode tables with diverse layouts. |
Qingping Yang; Yixuan Cao; Ping Luo; |
| 217 | Learning Task-relevant Representations for Generalization Via Characteristic Functions of Reward Sequence Distributions Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, visual distractions—which are common in real scenes—from high-dimensional observations can be hurtful to the learned representations in visual RL, thus degrading the performance of generalization. To tackle this problem, we propose a novel approach, namely Characteristic Reward Sequence Prediction (CRESP), to extract the task-relevant information by learning reward sequence distributions (RSDs), as the reward signals are task-relevant in RL and invariant to visual distractions. |
Rui Yang; Jie Wang; Zijie Geng; Mingxuan Ye; Shuiwang Ji; Bin Li; Feng Wu; |
| 218 | Reinforcement Subgraph Reasoning for Fake News Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In particular, we propose a reinforced subgraph generation method, and perform fine-grained modeling on the generated subgraphs by developing a Hierarchical Path-aware Kernel Graph Attention Network. |
Ruichao Yang; Xiting Wang; Yiqiao Jin; Chaozhuo Li; Jianxun Lian; Xing Xie; |
| 219 | Multi-Behavior Hypergraph-Enhanced Transformer for Sequential Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Despite their effectiveness, existing methods have far focused on item sequence representation with singular type of interactions, and thus are limited to capture dynamic heterogeneous relational structures between users and items (e.g., page view, add-to-favorite, purchase). To tackle this challenge, we design a Multi-Behavior Hypergraph-enhanced T ransformer framework (MBHT) to capture both short-term and long-term cross-type behavior dependencies. |
Yuhao Yang; Chao Huang; Lianghao Xia; Yuxuan Liang; Yanwei Yu; Chenliang Li; |
| 220 | TrajGAT: A Graph-based Long-term Dependency Modeling Approach for Trajectory Similarity Computation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel graph-based method, namely TrajGAT, to explicitly model the hierarchical spatial structure and improve the performance of long trajectory similarity computation. |
Di Yao; Haonan Hu; Lun Du; Gao Cong; Shi Han; Jingping Bi; |
| 221 | Learning Classifiers Under Delayed Feedback with A Time Window Assumption Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, existing studies reported that simply using a subset of all samples based on the time window assumption does not perform well, and that using all samples along with the time window assumption improves empirical performance. We extend these existing studies and propose a method with the unbiased and convex empirical risk that is constructed from all samples under the time window assumption. |
Shota Yasui; Masahiro Kato; |
| 222 | Learning The Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To equip the graph neural network with a flexible and practical graph structure, in this paper, we investigate how to model the evolutionary and multi-scale interactions of time series. |
Junchen Ye; Zihan Liu; Bowen Du; Leilei Sun; Weimiao Li; Yanjie Fu; Hui Xiong; |
| 223 | LeapAttack: Hard-Label Adversarial Attack on Text Via Gradient-Based Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a gradient-based optimization method named LeapAttack to craft high-quality text adversarial examples in the hard-label setting. |
Muchao Ye; Jinghui Chen; Chenglin Miao; Ting Wang; Fenglong Ma; |
| 224 | Deconfounding Actor-Critic Network with Policy Adaptation for Dynamic Treatment Regimes Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this study, we develop a new deconfounding actor-critic network (DAC) to learn optimal DTR policies for patients. |
Changchang Yin; Ruoqi Liu; Jeffrey Caterino; Ping Zhang; |
| 225 | Nimble GNN Embedding with Tensor-Train Decomposition Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper describes a new method for representing embedding tables of graph neural networks (GNNs) more compactly via tensor-train (TT) decomposition. |
Chunxing Yin; Da Zheng; Israt Nisa; Christos Faloutsos; George Karypis; Richard Vuduc; |
| 226 | Accurate Node Feature Estimation with Structured Variational Graph Autoencoder Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose SVGA (Structured Variational Graph Autoencoder), an accurate method for feature estimation. |
Jaemin Yoo; Hyunsik Jeon; Jinhong Jung; U Kang; |
| 227 | Adaptive Model Pooling for Online Deep Anomaly Detection from A Complex Evolving Data Stream Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper presents a framework for online deep anomaly detection, ARCUS, which can be instantiated with any autoencoder-based deep anomaly detection methods. |
Susik Yoon; Youngjun Lee; Jae-Gil Lee; Byung Suk Lee; |
| 228 | ROLAND: Graph Learning Framework for Dynamic Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Here we propose ROLAND, an effective graph representation learning framework for real-world dynamic graphs. |
Jiaxuan You; Tianyu Du; Jure Leskovec; |
| 229 | Availability Attacks Create Shortcuts Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Availability attacks, which poison the training data with imperceptible perturbations, can make the data not exploitable by machine learning algorithms so as to prevent unauthorized use of data. In this work, we investigate why these perturbations work in principle. |
Da Yu; Huishuai Zhang; Wei Chen; Jian Yin; Tie-Yan Liu; |
| 230 | Multiplex Heterogeneous Graph Convolutional Network Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, most existing works ignore the relation heterogeneity with multiplex network between multi-typed nodes and different importance of relations in meta-paths for node embedding, which can hardly capture the heterogeneous structure signals across different relations. To tackle this challenge, this work proposes a Multiplex Heterogeneous Graph Convolutional Network (MHGCN) for heterogeneous network embedding. |
Pengyang Yu; Chaofan Fu; Yanwei Yu; Chao Huang; Zhongying Zhao; Junyu Dong; |
| 231 | MDP2 Forest: A Constrained Continuous Multi-dimensional Policy Optimization Approach for Short-video Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we formalize the exposure proportion strategy as a policy-making problem with multi-dimensional continuous treatment under certain constraints from a causal inference point of view. |
Sizhe Yu; Ziyi Liu; Shixiang Wan; Jia Zheng; Zang Li; Fan Zhou; |
| 232 | Intrinsic-Motivated Sensor Management: Exploring with Physical Surprise Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper develops physics-embedded and self-supervised reinforcement learning for sensor management using an intrinsic reward. |
Jingyi Yuan; Yang Weng; Erik Blasch; |
| 233 | Dual Bidirectional Graph Convolutional Networks for Zero-shot Node Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a Dual Bidirectional Graph Convolutional Networks (DBiGCN) that consists of dual BiGCNs from the perspective of the nodes and the classes, respectively. |
Qin Yue; Jiye Liang; Junbiao Cui; Liang Bai; |
| 234 | M3Care: Learning with Missing Modalities in Multimodal Healthcare Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To relieve the underdetermined system, we propose a model solving a direct problem, dubbed learning with Missing Modalities in Multimodal healthcare data (M3Care). |
Chaohe Zhang; Xu Chu; Liantao Ma; Yinghao Zhu; Yasha Wang; Jiangtao Wang; Junfeng Zhao; |
| 235 | Variational Graph Author Topic Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Given above two challenges, we propose a Variational Graph Author Topic Model for documents to integrate both semantic interpretability and authorship and venue modeling into a unified VGAE framework. |
Delvin Ce Zhang; Hady W. Lauw; |
| 236 | Physics-infused Machine Learning for Crowd Simulation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose to jointly leverage the strength of the physical and neural network models for crowd simulation by a Physics-Infused Machine Learning (PIML) framework. |
Guozhen Zhang; Zihan Yu; Depeng Jin; Yong Li; |
| 237 | Few-shot Heterogeneous Graph Learning Via Cross-domain Knowledge Transfer Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, we study the cross-domain few-shot learning problem over HGs and develop a novel model for Cross-domain Heterogeneous Graph Meta learning (CrossHG-Meta). |
Qiannan Zhang; Xiaodong Wu; Qiang Yang; Chuxu Zhang; Xiangliang Zhang; |
| 238 | M-Mix: Generating Hard Negatives Via Multi-sample Mixing for Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Inspired by recent hard negative mining methods via pairwise mixup operation in vision, we propose M-Mix, which dynamically generates a sequence of hard negatives. |
Shaofeng Zhang; Meng Liu; Junchi Yan; Hengrui Zhang; Lingxiao Huang; Xiaokang Yang; Pinyan Lu; |
| 239 | Multi-Agent Graph Convolutional Reinforcement Learning for Dynamic Electric Vehicle Charging Pricing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, in this paper, we propose a Multi-Agent Graph Convolutional Reinforcement Learning (MAGC) framework to enable CSOs to achieve more effective use of these stations by providing dynamic pricing for each of the continuously arising charging requests with optimizing multiple long-term commercial goals. |
Weijia Zhang; Hao Liu; Jindong Han; Yong Ge; Hui Xiong; |
| 240 | MetroGAN: Simulating Urban Morphology with Generative Adversarial Network Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Here, we propose a GAN framework with geographical knowledge, namely Metropolitan GAN (MetroGAN), for urban morphology simulation. |
Weiyu Zhang; Yiyang Ma; Di Zhu; Lei Dong; Yu Liu; |
| 241 | Model Degradation Hinders Deep Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we disentangle the conventional graph convolution operation into two independent operations: Propagation (P) and Transformation (T). |
Wentao Zhang; Zeang Sheng; Ziqi Yin; Yuezihan Jiang; Yikuan Xia; Jun Gao; Zhi Yang; Bin Cui; |
| 242 | Counteracting User Attention Bias in Music Streaming Recommendation Via Reward Modification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a learning-based counterfactual approach to adjusting the user auto-feedbacks and learning the recommendation models using Neural Dueling Bandit algorithm, called NDB. |
Xiao Zhang; Sunhao Dai; Jun Xu; Zhenhua Dong; Quanyu Dai; Ji-Rong Wen; |
| 243 | Improving Social Network Embedding Via New Second-Order Continuous Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a semi-model-agnostic method based on our model to enhance the prediction explanation using high-order information. |
Yanfu Zhang; Shangqian Gao; Jian Pei; Heng Huang; |
| 244 | COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we show that the node embedding obtained via the graph augmentations is highly biased, somewhat limiting contrastive models from learning discriminative features for downstream tasks.Thus, instead of investigating graph augmentation in the input space, we alternatively propose to perform augmentations on the hidden features (feature augmentation). |
Yifei Zhang; Hao Zhu; Zixing Song; Piotr Koniusz; Irwin King; |
| 245 | Unsupervised Key Event Detection from Massive Text Corpora Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a new task, key event detection at the intermediate level, which aims to detect from a news corpus key events (e.g., "HK Airport Protest on Aug. 12-14"), each happening at a particular time/location and focusing on the same topic. |
Yunyi Zhang; Fang Guo; Jiaming Shen; Jiawei Han; |
| 246 | FLDetector: Defending Federated Learning Against Model Poisoning Attacks Via Detecting Malicious Clients Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: It is still an open challenge how to defend against model poisoning attacks with a large number of malicious clients. Our FLDetector addresses this challenge via detecting malicious clients. |
Zaixi Zhang; Xiaoyu Cao; Jinyuan Jia; Neil Zhenqiang Gong; |
| 247 | Adaptive Learning for Weakly Labeled Streams Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: When the data are constantly gathered with unknown noise on labels, it is quite challenging to design algorithms to obtain a well-generalized classifier. To address this difficulty, we propose a novel noise transition matrix estimation approach for data streams with scarce noisy labels by online anchor points identification. |
Zhen-Yu Zhang; Yu-Yang Qian; Yu-Jie Zhang; Yuan Jiang; Zhi-Hua Zhou; |
| 248 | Adaptive Fairness-Aware Online Meta-Learning for Changing Environments Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address the fairness-aware online learning problem in changing environments, in this paper, we first construct a novel regret metric FairSAR by adding long-term fairness constraints onto a strongly adapted loss regret. Furthermore, to determine a good model parameter at each round, we propose a novel adaptive fairness-aware online meta-learning algorithm, namely FairSAOML, which is able to adapt to changing environments in both bias control and model precision. |
Chen Zhao; Feng Mi; Xintao Wu; Kai Jiang; Latifur Khan; Feng Chen; |
| 249 | MT-FlowFormer: A Semi-Supervised Flow Transformer for Encrypted Traffic Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, these works still suffer from two main intrinsic limitations: (1) the feature extraction process lacks a mechanism to take into account correlations between flows in the flow sequence; and (2) a large volume of manually-labeled data is required for training an effective deep classifier. In this paper, we propose a novel semi-supervised framework to address these problems. |
Ruijie Zhao; Xianwen Deng; Zhicong Yan; Jun Ma; Zhi Xue; Yijun Wang; |
| 250 | Integrity Authentication in Tree Models Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we study the problem of model integrity authentication in tree models. |
Weijie Zhao; Yingjie Lao; Ping Li; |
| 251 | Contrastive Learning with Complex Heterogeneity Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To overcome the issues, in this paper, we propose a unified heterogeneous learning framework, which combines both the weighted unsupervised contrastive loss and the weighted supervised contrastive loss to model multiple types of heterogeneity. |
Lecheng Zheng; Jinjun Xiong; Yada Zhu; Jingrui He; |
| 252 | Instant Graph Neural Networks for Dynamic Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose Instant Graph Neural Network (InstantGNN), an incremental computation approach for the graph representation matrix of dynamic graphs. |
Yanping Zheng; Hanzhi Wang; Zhewei Wei; Jiajun Liu; Sibo Wang; |
| 253 | KRATOS: Context-Aware Cell Type Classification and Interpretation Using Joint Dimensionality Reduction and Clustering Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In our system, KRATOS, we alter the three-step workflow to a two-step one, where we jointly optimize the first two steps and add the third (interpretability) step to form an integrated sc-RNA-seq analysis pipeline. |
Zihan Zhou; Zijia Du; Somali Chaterji; |
| 254 | Unified 2D and 3D Pre-Training of Molecular Representations Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We note that most previous work handles 2D and 3D information separately, while jointly leveraging these two sources may foster a more informative representation. In this work, we explore this appealing idea and propose a new representation learning method based on a unified 2D and 3D pre-training. |
Jinhua Zhu; Yingce Xia; Lijun Wu; Shufang Xie; Tao Qin; Wengang Zhou; Houqiang Li; Tie-Yan Liu; |
| 255 | How Does Heterophily Impact The Robustness of Graph Neural Networks?: Theoretical Connections and Practical Implications Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We bridge two research directions on graph neural networks (GNNs), by formalizing the relation between heterophily of node labels (i.e., connected nodes tend to have dissimilar labels) and the robustness of GNNs to adversarial attacks. |
Jiong Zhu; Junchen Jin; Donald Loveland; Michael T. Schaub; Danai Koutra; |
| 256 | A Nearly-Linear Time Algorithm for Minimizing Risk of Conflict in Social Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we study the problem of minimizing risk of conflict in social networks by modifying the initial opinions of a small number of nodes. |
Liwang Zhu; Zhongzhi Zhang; |
| 257 | A Process-Aware Decision Support System for Business Processes Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Overlooking some of the essential factors or lack of knowledge can impact the throughput and business outcomes. Therefore, we propose an end-to-end automated decision support system with explanation for business processes. |
Prerna Agarwal; Buyu Gao; Siyu Huo; Prabhat Reddy; Sampath Dechu; Yazan Obeidi; Vinod Muthusamy; Vatche Isahagian; Sebastian Carbajales; |
| 258 | RCAD: Real-time Collaborative Anomaly Detection System for Mobile Broadband Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose, RCAD, a novel distributed architecture for detecting anomalies in network data forwarding latency in an unsupervised fashion. |
Azza H. Ahmed; Michael A. Riegler; Steven A. Hicks; Ahmed Elmokashfi; |
| 259 | Generalizable Floorplanner Through Corner Block List Representation and Hypergraph Embedding Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a novel deep reinforcement learning agent to perform floorplanning, one of the early stages of VLSI physical design. |
Mohammad Amini; Zhanguang Zhang; Surya Penmetsa; Yingxue Zhang; Jianye Hao; Wulong Liu; |
| 260 | ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: At Pinterest, we build a single set of product embeddings called ItemSage to provide relevant recommendations in all shopping use cases including user, image and search based recommendations. |
Paul Baltescu; Haoyu Chen; Nikil Pancha; Andrew Zhai; Jure Leskovec; Charles Rosenberg; |
| 261 | Company-as-Tribe: Company Financial Risk Assessment on Tribe-Style Graph with Hierarchical Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a novel Hierarchical Graph Neural Network (TH-GNN) for Tribe-style graphs via two levels, with the first level to encode the structure pattern of the tribes with contrastive learning, and the second level to diffuse information based on the inter-tribe relations, achieving effective and efficient risk assessment. |
Wendong Bi; Bingbing Xu; Xiaoqian Sun; Zidong Wang; Huawei Shen; Xueqi Cheng; |
| 262 | Personalized Chit-Chat Generation for Recommendation Using External Chat Corpora Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We find with a user study that generating appropriate chit-chat for news articles can help expand user interest and increase the probability that a user reads a recommended news article. Based on this observation, we propose a method to generate personalized chit-chat for news recommendation. |
Changyu Chen; Xiting Wang; Xiaoyuan Yi; Fangzhao Wu; Xing Xie; Rui Yan; |
| 263 | EXTR: Click-Through Rate Prediction with Externalities in E-Commerce Sponsored Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Facing the above challenges, inspired by the Transformer, we propose EXternality TRansformer (EXTR) which regards target ad with all slots as query and external items as key&value to model externalities in all exposure situations in parallel. |
Chi Chen; Hui Chen; Kangzhi Zhao; Junsheng Zhou; Li He; Hongbo Deng; Jian Xu; Bo Zheng; Yong Zhang; Chunxiao Xing; |
| 264 | BrainNet: Epileptic Wave Detection from SEEG with Hierarchical Graph Diffusion Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Moreover, the nature of epileptic waves and SEEG data inevitably leads to extremely imbalanced labels and severe noise. To address these challenges, we propose a novel model (BrainNet) that jointly learns the dynamic diffusion graphs and models the brain wave diffusion patterns. |
Junru Chen; Yang Yang; Tao Yu; Yingying Fan; Xiaolong Mo; Carl Yang; |
| 265 | Physics-Guided Graph Meta Learning for Predicting Water Temperature and Streamflow in Stream Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a graph-based meta learning approach to separately predict water quantity and quality variables for river segments in stream networks. |
Shengyu Chen; Jacob A. Zwart; Xiaowei Jia; |
| 266 | AntiBenford Subgraphs: Unsupervised Anomaly Detection in Financial Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose the AntiBenford subgraph framework that is founded on well-established statistical principles. |
Tianyi Chen; Charalampos Tsourakakis; |
| 267 | Interpreting Trajectories from Multiple Views: A Hierarchical Self-Attention Network for Estimating The Time of Arrival Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To overcome the limitation, this study proposes multi-view trajectory representation that comprehensively interprets a trajectory from the segment-, link-, and intersection-views. |
Zebin Chen; Xiaolin Xiao; Yue-Jiao Gong; Jun Fang; Nan Ma; Hua Chai; Zhiguang Cao; |
| 268 | ILASR: Privacy-Preserving Incremental Learning for Automatic Speech Recognition at Production Scale Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Motivated by these challenges, in this paper we use a cloud based framework for production systems to demonstrate insights from privacy preserving incremental learning for automatic speech recognition (ILASR). |
Gopinath Chennupati; Milind Rao; Gurpreet Chadha; Aaron Eakin; Anirudh Raju; Gautam Tiwari; Anit Kumar Sahu; Ariya Rastrow; Jasha Droppo; Andy Oberlin; Buddha Nandanoor; Prahalad Venkataramanan; Zheng Wu; Pankaj Sitpure; |
| 269 | Graph-based Multilingual Language Model: Leveraging Product Relations for Search Relevance Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we formulate search relevance as a multi-class classification problem and propose a graph-based solution to classify a given query-item pair as exact, substitute, complement, or irrelevant (ESCI). |
Nurendra Choudhary; Nikhil Rao; Karthik Subbian; Chandan K. Reddy; |
| 270 | Ask to Know More: Generating Counterfactual Explanations for Fake Claims Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose elucidating fact-checking predictions using counterfactual explanations to help people understand why a specific piece of news was identified as fake. |
Shih-Chieh Dai; Yi-Li Hsu; Aiping Xiong; Lun-Wei Ku; |
| 271 | The Good, The Bad, and The Outliers: A Testing Framework for Decision Optimization Model Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce an open-source framework designed for large-scale testing and solution quality analysis of DO model learning algorithms. |
Orit Davidovich; Gheorghe-Teodor Bercea; Segev Wasserkrug; |
| 272 | Amazon Shop The Look: A Visual Search System for Fashion and Home Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we introduce Shop the Look, a web-scale fashion and home product visual search system deployed at Amazon. |
Ming Du; Arnau Ramisa; Amit Kumar K C; Sampath Chanda; Mengjiao Wang; Neelakandan Rajesh; Shasha Li; Yingchuan Hu; Tao Zhou; Nagashri Lakshminarayana; Son Tran; Doug Gray; |
| 273 | Affective Signals in A Social Media Recommender System Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper describes the challenges and solutions we developed to apply Affective Computing to social media recommendation systems. |
Jane Dwivedi-Yu; Yi-Chia Wang; Lijing Qin; Cristian Canton-Ferrer; Alon Y. Halevy; |
| 274 | TwHIN: Embedding The Twitter Heterogeneous Information Network for Personalized Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we investigate knowledge-graph embeddings for entities in the Twitter HIN (TwHIN); we show that these pretrained representations yield significant offline and online improvement for a diverse range of downstream recommendation and classification tasks: personalized ads rankings, account follow-recommendation, offensive content detection, and search ranking. |
Ahmed El-Kishky; Thomas Markovich; Serim Park; Chetan Verma; Baekjin Kim; Ramy Eskander; Yury Malkov; Frank Portman; Sofía Samaniego; Ying Xiao; Aria Haghighi; |
| 275 | Automatic Generation of Product-Image Sequence in E-commerce Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To address these challenges, in this paper, we present a new learning framework in order to achieve Automatic Generation of Product-Image Sequence (AGPIS) in e-commerce. |
Xiaochuan Fan; Chi Zhang; Yong Yang; Yue Shang; Xueying Zhang; Zhen He; Yun Xiao; Bo Long; Lingfei Wu; |
| 276 | SAMCNet: Towards A Spatially Explainable AI Approach for Classifying MxIF Oncology Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In addition, the related deep neural networks are limited to category pairs and do not explore larger subsets of point categories. To overcome these limitations, we propose a Spatial-interaction Aware Multi-Category deep neural Network (SAMCNet) architecture and contribute novel local reference frame characterization and point pair prioritization layers for spatially explainable classification. |
Majid Farhadloo; Carl Molnar; Gaoxiang Luo; Yan Li; Shashi Shekhar; Rachel L. Maus; Svetomir Markovic; Alexey Leontovich; Raymond Moore; |
| 277 | Large-Scale Acoustic Automobile Fault Detection: Diagnosing Engines Through Sound Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we present AMPNet, an acoustic abnormality detection model deployed at ACV Auctions to automatically identify engine faults of vehicles listed on the ACV Auctions platform. |
Dennis Fedorishin; Justas Birgiolas; Deen Dayal Mohan; Livio Forte; Philip Schneider; Srirangaraj Setlur; Venu Govindaraju; |
| 278 | Precise Mobility Intervention for Epidemic Control Using Unobservable Information Via Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a Variational hiErarcHICal reinforcement Learning method for Epidemic control via individual-level mobility intervention, namely Vehicle. |
Tao Feng; Tong Xia; Xiaochen Fan; Huandong Wang; Zefang Zong; Yong Li; |
| 279 | Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9.3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system. |
Jack FitzGerald; Shankar Ananthakrishnan; Konstantine Arkoudas; Davide Bernardi; Abhishek Bhagia; Claudio Delli Bovi; Jin Cao; Rakesh Chada; Amit Chauhan; Luoxin Chen; Anurag Dwarakanath; Satyam Dwivedi; Turan Gojayev; Karthik Gopalakrishnan; Thomas Gueudre; Dilek Hakkani-Tur; Wael Hamza; Jonathan J. Hüser; Kevin Martin Jose; Haidar Khan; Beiye Liu; Jianhua Lu; Alessandro Manzotti; Pradeep Natarajan; Karolina Owczarzak; Gokmen Oz; Enrico Palumbo; Charith Peris; Chandana Satya Prakash; Stephen Rawls; Andy Rosenbaum; Anjali Shenoy; Saleh Soltan; Mukund Harakere Sridhar; Lizhen Tan; Fabian Triefenbach; Pan Wei; Haiyang Yu; Shuai Zheng; Gokhan Tur; Prem Natarajan; |
| 280 | DP-GAT: A Framework for Image-based Disease Progression Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a framework called DP-GAT to identify regions containing significant biological structures and model the relationships among these regions as a graph along with their respective contexts. |
Alex Foo; Wynne Hsu; Mong Li Lee; Gavin S. W. Tan; |
| 281 | Graph Meta-Reinforcement Learning for Transferable Autonomous Mobility-on-Demand Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, real-world system operators can hardly afford to fully re-train AMoD controllers for every city they operate in, as this could result in a high number of poor-quality decisions during training, making the single-city strategy a potentially impractical solution. To address these limitations, we propose to formalize the multi-city AMoD problem through the lens of meta-reinforcement learning (meta-RL) and devise an actor-critic algorithm based on recurrent graph neural networks. |
Daniele Gammelli; Kaidi Yang; James Harrison; Filipe Rodrigues; Francisco Pereira; Marco Pavone; |
| 282 | Applying Deep Learning Based Probabilistic Forecasting to Food Preparation Time for On-Demand Delivery Service Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we apply probabilistic forecasting to FPT for the first time and propose a non-parametric method based on deep learning. |
Chengliang Gao; Fan Zhang; Yue Zhou; Ronggen Feng; Qiang Ru; Kaigui Bian; Renqing He; Zhizhao Sun; |
| 283 | Collaborative Intelligence Orchestration: Inconsistency-Based Fusion of Semi-Supervised Learning and Active Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Motivated by the industry practice of labeling data, we propose an innovative Inconsistency-based virtual aDvErsarial Active Learning (IDEAL) algorithm to further investigate SSL-AL’s potential superiority and achieve mutual enhancement of AL and SSL, i.e., SSL propagates label information to unlabeled samples and provides smoothed embeddings for AL, while AL excludes samples with inconsistent predictions and considerable uncertainty for SSL. |
Jiannan Guo; Yangyang Kang; Yu Duan; Xiaozhong Liu; Siliang Tang; Wenqiao Zhang; Kun Kuang; Changlong Sun; Fei Wu; |
| 284 | Automatic Controllable Product Copywriting for E-Commerce Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we report our experience in deploying an E-commerce Prefix-based Controllable Copywriting Generation (EPCCG) system into the JD.com e-commerce product recommendation platform. |
Xiaojie Guo; Qingkai Zeng; Meng Jiang; Yun Xiao; Bo Long; Lingfei Wu; |
| 285 | Talent Demand-Supply Joint Prediction with Dynamic Heterogeneous Graph Enhanced Meta-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, in this paper, we propose a Dynamic Heterogeneous Graph Enhanced Meta-learning (DH-GEM) framework for fine-grained talent demand-supply joint prediction. |
Zhuoning Guo; Hao Liu; Le Zhang; Qi Zhang; Hengshu Zhu; Hui Xiong; |
| 286 | Real-Time Rideshare Driver Supply Values Using Online Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present Online Supply Values (OSV), a system for estimating the return of available rideshare drivers to match drivers to ride requests at Lyft. |
Benjamin Han; Hyungjun Lee; Sébastien Martin; |
| 287 | Learning Sparse Latent Graph Representations for Anomaly Detection in Multivariate Time Series Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we introduce Fused Sparse Autoencoder and Graph Net (FuSAGNet), which jointly optimizes reconstruction and forecasting while explicitly modeling the relationships within multivariate time series. |
Siho Han; Simon S. Woo; |
| 288 | Three-Stage Root Cause Analysis for Logistics Time Efficiency Via Explainable Machine Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, the delay in logistics transportation and delivery can still happen due to various practical issues, which significantly impact the quality of logistics service. In order to address this issue, this work investigates the root causes impacting the time efficiency, thereby facilitating the operation of logistics systems such that resources can be appropriately allocated to improve the performance. |
Shiqi Hao; Yang Liu; Yu Wang; Yuan Wang; Wenming Zhe; |
| 289 | Unsupervised Learning Style Classification for Learning Path Generation in Online Education Platforms Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we give a formal definition of the unsupervised LSC problem and summarize the domain knowledge into problem-solving heuristics (which addresses C1). |
Zhicheng He; Wei Xia; Kai Dong; Huifeng Guo; Ruiming Tang; Dingyin Xia; Rui Zhang; |
| 290 | Greykite: Deploying Flexible Forecasting at Scale at LinkedIn Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We present Greykite, an open-source Python library for forecasting that has been deployed on over twenty use cases at LinkedIn. |
Reza Hosseini; Albert Chen; Kaixu Yang; Sayan Patra; Yi Su; Saad Eddin Al Orjany; Sishi Tang; Parvez Ahammad; |
| 291 | Learning Backward Compatible Embeddings Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Our key idea is that whenever a new embedding model is trained, we learn it together with a light-weight backward compatibility transformation that aligns the new embedding to the previous version of it. |
Weihua Hu; Rajas Bansal; Kaidi Cao; Nikhil Rao; Karthik Subbian; Jure Leskovec; |
| 292 | ERNIE-GeoL: A Geography-and-Language Pre-trained Model and Its Applications in Baidu Maps Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: One of the main reasons for this plateau is the lack of readily available geographic knowledge in generic PTMs. To address this problem, in this paper, we present ERNIE-GeoL, which is a geography-and-language pre-trained model designed and developed for improving the geo-related tasks at Baidu Maps. |
Jizhou Huang; Haifeng Wang; Yibo Sun; Yunsheng Shi; Zhengjie Huang; An Zhuo; Shikun Feng; |
| 293 | DuIVA: An Intelligent Voice Assistant for Hands-free and Eyes-free Voice Interaction with The Baidu Maps App Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present our efforts and findings of a 4-year longitudinal study on designing and implementing DuIVA, which is an intelligent voice assistant (IVA) embedded in the Baidu Maps app for hands-free, eyes-free human-to-app interaction in a fully voice-controlled manner. |
Jizhou Huang; Haifeng Wang; Shiqiang Ding; Shaolei Wang; |
| 294 | Rax: Composable Learning-to-Rank Using JAX Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: The goal of Rax is to facilitate easy prototyping of LTR systems by leveraging the flexibility and simplicity of JAX. |
Rolf Jagerman; Xuanhui Wang; Honglei Zhuang; Zhen Qin; Michael Bendersky; Marc Najork; |
| 295 | A Fully Differentiable Set Autoencoder Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Leveraging deep representation learning, we propose a generic, robust and systematic model that is able to combine multiple data modalities in a permutation and modes-number-invariant fashion, both fundamental properties to properly face changes in data type content and availability. |
Nikita Janakarajan; Jannis Born; Matteo Manica; |
| 296 | Precision CityShield Against Hazardous Chemicals Threats Via Location Mining and Self-Supervised Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: How to recognize these unknown HCLs and identify their risk levels is an essential task for urban hazardous chemicals management. To accomplish this task, in this work, we propose a system named as CityShield to discover hidden HCLs and classify their risk levels based on trajectories of hazardous chemicals transportation vehicles. |
Jiahao Ji; Jingyuan Wang; Junjie Wu; Boyang Han; Junbo Zhang; Yu Zheng; |
| 297 | Augmenting Log-based Anomaly Detection Models to Reduce False Anomalies with Human Feedback Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Through the study, we identify four typical anti-patterns that affect the detection results the most. Based on these patterns, we propose HiLog, an effective human-in-the-loop log-based anomaly detection approach that integrates human knowledge to augment anomaly detection models. |
Tong Jia; Ying Li; Yong Yang; Gang Huang; Zhonghai Wu; |
| 298 | T-Cell Receptor-Peptide Interaction Prediction with Physical Model Augmented Pseudo-Labeling Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To combat the data scarcity issue presented in the current datasets, we propose to extend the training dataset by physical modeling of TCR-peptide pairs. |
Yiren Jian; Erik Kruus; Martin Renqiang Min; |
| 299 | Analyzing Online Transaction Networks with Network Motifs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we analyze online transaction networks from the perspective of network motif. |
Jiawei Jiang; Yusong Hu; Xiaosen Li; Wen Ouyang; Zhitao Wang; Fangcheng Fu; Bin Cui; |
| 300 | Predicting Bearings Degradation Stages for Predictive Maintenance in The Pharmaceutical Industry Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we focus on rolling-elements bearings and we propose a framework for predicting their degradation stages automatically. |
Dovile Juodelyte; Veronika Cheplygina; Therese Graversen; Philippe Bonnet; |
| 301 | Vexation-Aware Active Learning for On-Menu Restaurant Dish Availability Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we study the problem of Vexation-Aware Active Learning (VAAL), where judiciously selected questions are targeted towards improving restaurant-dish model prediction, subject to a limit on the percentage of "unsure” answers or "dismissals” (e.g., swiping the app closed) measuring user vexation. |
Jean-François Kagy; Flip Korn; Afshin Rostamizadeh; Chris Welty; |
| 302 | COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a novel method that uses prefix control tokens along with BART [16] fine-tuning. |
Yashal Shakti Kanungo; Gyanendra Das; Pooja A; Sumit Negi; |
| 303 | Preventing Catastrophic Forgetting in Continual Learning of New Natural Language Tasks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we approach the problem of incrementally expanding MTL models’ capability to solve new tasks over time by distilling the knowledge of an already trained model on n tasks into a new one for solving n+1 tasks. |
Sudipta Kar; Giuseppe Castellucci; Simone Filice; Shervin Malmasi; Oleg Rokhlenko; |
| 304 | SoccerCPD: Formation and Role Change-Point Detection in Soccer Matches Using Spatiotemporal Tracking Data Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, existing approaches either assume that team formation is consistent throughout a match or assign formations frame-by-frame, which disagree with real situations. To tackle this issue, we propose a change-point detection framework named SoccerCPD that distinguishes tactically intended formation and role changes from temporary changes in soccer matches. |
Hyunsung Kim; Bit Kim; Dongwook Chung; Jinsung Yoon; Sang-Ki Ko; |
| 305 | Fast Mining and Forecasting of Co-evolving Epidemiological Data Streams Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a new streaming algorithm, EPICAST, which is able to model, understand and forecast dynamical patterns in large co-evolving epidemiological data streams. |
Tasuku Kimura; Yasuko Matsubara; Koki Kawabata; Yasushi Sakurai; |
| 306 | A/B Testing Intuition Busters: Common Misunderstandings in Online Controlled Experiments Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: While the statistics behind controlled experiments are well documented and some basic pitfalls known, we have observed some seemingly intuitive concepts being touted, including by A/B tool vendors and agencies, which are misleading, often badly so. Our goal is to describe these misunderstandings, the "intuition" behind them, and to explain and bust that intuition with solid statistical reasoning. |
Ron Kohavi; Alex Deng; Lukas Vermeer; |
| 307 | Multi-Aspect Dense Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose to explicitly represent multiple aspects using one embedding per aspect. |
Weize Kong; Swaraj Khadanga; Cheng Li; Shaleen Kumar Gupta; Mingyang Zhang; Wensong Xu; Michael Bendersky; |
| 308 | Self-Supervised Augmentation and Generation for Multi-lingual Text Advertisements at Bing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a unified Self-Supervised Augmentation and Generation (SAG) architecture to handle the multi-lingual text advertisements generation task in a real production scenario. |
Xiaoyu Kou; Tianqi Zhao; Fan Zhang; Song Li; Qi Zhang; |
| 309 | A New Generation of Perspective API: Efficient Multilingual Character-level Transformers Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present the fundamentals behind the next version of the Perspective API from Google Jigsaw. |
Alyssa Lees; Vinh Q. Tran; Yi Tay; Jeffrey Sorensen; Jai Gupta; Donald Metzler; Lucy Vasserman; |
| 310 | EdgeWatch: Collaborative Investigation of Data Integrity at The Edge Based on Blockchain Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: There are two main challenges in practice: 1) there is a lack of Byzantine-tolerant collaborative investigation method; and 2) edge servers may be reluctant to collaborate without proper incentives. To tackle these challenges systematically, this paper proposes a novel scheme named EdgeWatch to enable robust and collaborative EDI investigation in a decentralized manner based on blockchain. |
Bo Li; Qiang He; Liang Yuan; Feifei Chen; Lingjuan Lyu; Yun Yang; |
| 311 | Design Domain Specific Neural Network Via Symbolic Testing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: A systematic investigation over simulated data reveals the fact that the self-attention architecture fails to learn some standard symbolic expressions like the count distinct operation. To overcome this deficiency, we propose a novel architecture named SHORING, which contains two components:event network andsequence network. |
Hui Li; Xing Fu; Ruofan Wu; Jinyu Xu; Kai Xiao; Xiaofu Chang; Weiqiang Wang; Shuai Chen; Leilei Shi; Tao Xiong; Yuan Qi; |
| 312 | Causal Inference-Based Root Cause Analysis for Online Service Systems with Intervention Recognition Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we formulate the root cause analysis problem as a new causal inference task namedintervention recognition. |
Mingjie Li; Zeyan Li; Kanglin Yin; Xiaohui Nie; Wenchi Zhang; Kaixin Sui; Dan Pei; |
| 313 | AutoFAS: Automatic Feature and Architecture Selection for Pre-Ranking System Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, a novel framework AutoFAS is proposed which jointly optimizes the efficiency and effectiveness of the pre-ranking model: (i) AutoFAS for the first time simultaneously selects the most valuable features and network architectures using Neural Architecture Search (NAS) technique; (ii) equipped with ranking model guided reward during NAS procedure, AutoFAS can select the best pre-ranking architecture for a given ranking teacher without any computation overhead. |
Xiang Li; Xiaojiang Zhou; Yao Xiao; Peihao Huang; Dayao Chen; Sheng Chen; Yunsen Xian; |
| 314 | Arbitrary Distribution Modeling with Censorship in Real-Time Bidding Advertising Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we devise a novel loss function, Neighborhood Likelihood Loss (NLL), collaborating with a proposed framework, Arbitrary Distribution Modeling (ADM), to predict the winning price distribution under censorship with no pre-assumption required. |
Xu Li; Michelle Ma Zhang; Zhenya Wang; Youjun Tong; |
| 315 | Automatically Discovering User Consumption Intents in Meituan Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: For the intent discovery decoder, we propose to build intent-pair pseudo labels based on the denoised feature similarities to transfer knowledge from known intents to new ones. |
Yinfeng Li; Chen Gao; Xiaoyi Du; Huazhou Wei; Hengliang Luo; Depeng Jin; Yong Li; |
| 316 | Towards Learning Disentangled Representations for Time Series Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose Disentangle Time-Series, a novel disentanglement enhancement framework for time series data. |
Yuening Li; Zhengzhang Chen; Daochen Zha; Mengnan Du; Jingchao Ni; Denghui Zhang; Haifeng Chen; Xia Hu; |
| 317 | TaxoTrans: Taxonomy-Guided Entity Translation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we tackle the task of taxonomy entity translation, which is to translate the names of taxonomy entities in a source language to a target language. |
Zhuliu Li; Yiming Wang; Xiao Yan; Weizhi Meng; Yanen Li; Jaewon Yang; |
| 318 | Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders Up to 100 Trillion Parameters Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, the training of such models is challenging even within industrial scale data centers. We resolve this challenge by careful co-design of both optimization algorithm and distributed system architecture. |
Xiangru Lian; Binhang Yuan; Xuefeng Zhu; Yulong Wang; Yongjun He; Honghuan Wu; Lei Sun; Haodong Lyu; Chengjun Liu; Xing Dong; Yiqiao Liao; Mingnan Luo; Congfei Zhang; Jingru Xie; Haonan Li; Lei Chen; Renjie Huang; Jianying Lin; Chengchun Shu; Xuezhong Qiu; Zhishan Liu; Dongying Kong; Lei Yuan; Hai Yu; Sen Yang; Ce Zhang; Ji Liu; |
| 319 | Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present Duplex Conversation, a multi-turn, multimodal spoken dialogue system that enables telephone-based agents to interact with customers like a human. |
Ting-En Lin; Yuchuan Wu; Fei Huang; Luo Si; Jian Sun; Yongbin Li; |
| 320 | AdaFS: Adaptive Feature Selection in Deep Recommender System Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose an adaptive feature selection framework, AdaFS, for deep recommender systems. |
Weilin Lin; Xiangyu Zhao; Yejing Wang; Tong Xu; Xian Wu; |
| 321 | A Logic Aware Neural Generation Method for Explainable Data-to-text Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we introduce a practical data-to-text method for the logic-critical scenario, specifically for anti-money laundering applications. |
Xiexiong Lin; Huaisong Li; Tao Huang; Feng Wang; Linlin Chao; Fuzhen Zhuang; Taifeng Wang; Tianyi Zhang; |
| 322 | Feature-aware Diversified Re-ranking with Disentangled Representations for Relevant Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Moreover, redundant or noisy item features might affect the performance of simple feature-aware recommendation approaches. Faced with these issues, we propose a Feature Disentanglement Self-Balancing Re-ranking framework (FDSB) to capture feature- aware diversity. |
Zihan Lin; Hui Wang; Jingshu Mao; Wayne Xin Zhao; Cheng Wang; Peng Jiang; Ji-Rong Wen; |
| 323 | Rapid Regression Detection in Software Deployments Through Sequential Testing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a statistical framework for rapidly detecting regressions in software deployments. |
Michael Lindon; Chris Sanden; Vaché Shirikian; |
| 324 | Task-optimized User Clustering Based on Mobile App Usage for Cold-start Recommendations Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address the challenges, we propose a tailored Dual Alignment User Clustering (DAUC) model, which applies a sample-wise contrastive alignment to eliminate the gap between active users’ mobile app usage and article reading behavior, and a distribution-wise adversarial alignment to eliminate the gap between active users’ and cold-start users’ app usage behavior. |
Bulou Liu; Bing Bai; Weibang Xie; Yiwen Guo; Hao Chen; |
| 325 | User Behavior Pre-training for Online Fraud Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, in this paper, we propose to pre-train user behavior sequences, which consist of orderly arranged actions, from the large-scale unlabeled data sources for online fraud detection. |
Can Liu; Yuncong Gao; Li Sun; Jinghua Feng; Hao Yang; Xiang Ao; |
| 326 | Modeling Persuasion Factor of User Decision for Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Existing recommendation engines ignore the explicit modeling of these factors, leading to sub-optimal recommendation performance. In this paper, we focus on the real-world scenario where these factors can be explicitly captured (the users are exposed with decision factor-based persuasion texts, i.e., persuasion factors). |
Chang Liu; Chen Gao; Yuan Yuan; Chen Bai; Lingrui Luo; Xiaoyi Du; Xinlei Shi; Hengliang Luo; Depeng Jin; Yong Li; |
| 327 | HiPAL: A Deep Framework for Physician Burnout Prediction Using Activity Logs in Electronic Health Records Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To utilize the large amount of unlabeled activity logs, we propose a semi-supervised framework that learns to transfer knowledge extracted from unlabeled clinician activities to the HiPAL-based prediction model. |
Hanyang Liu; Sunny S. Lou; Benjamin C. Warner; Derek R. Harford; Thomas Kannampallil; Chenyang Lu; |
| 328 | Lion: A GPU-Accelerated Online Serving System for Web-Scale Recommendation at Baidu Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a GPU-accelerated online serving system, namely Lion, which consists of the staged event-driven heterogeneous pipeline, unified memory manager, and automatic execution optimizer to handle web-scale traffic in a real-time and cost-effective way. |
Hao Liu; Qian Gao; Xiaochao Liao; Guangxing Chen; Hao Xiong; Silin Ren; Guobao Yang; Zhiwei Zha; |
| 329 | No One Left Behind: Inclusive Federated Learning Over Heterogeneous Devices Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: The straightforward solutions like removing the weak clients or using a small model to fit all clients will lead to some problems, such as under-representation of dropped clients and inferior accuracy due to data loss or limited model representation ability. In this work, we propose InclusiveFL, a client-inclusive federated learning method to handle this problem. |
Ruixuan Liu; Fangzhao Wu; Chuhan Wu; Yanlin Wang; Lingjuan Lyu; Hong Chen; Xing Xie; |
| 330 | Para-Pred: Addressing Heterogeneity for City-Wide Indoor Status Estimation in On-Demand Delivery Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose Para-Pred, an indoor status estimation framework based on the graph neural network, which directly Predicts the effective indoor status estimation model Parameters for unseen scenarios. |
Wei Liu; Yi Ding; Shuai Wang; Yu Yang; Desheng Zhang; |
| 331 | OAG-BERT: Towards A Unified Backbone Language Model for Academic Knowledge Services Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To create a unified backbone language model for various knowledge-intensive academic knowledge mining challenges, based on the world’s largest public academic graph Open Academic Graph (OAG), we pre-train an academic language model, namely OAG-BERT, to integrate massive heterogeneous entity knowledge beyond scientific corpora. |
Xiao Liu; Da Yin; Jingnan Zheng; Xingjian Zhang; Peng Zhang; Hongxia Yang; Yuxiao Dong; Jie Tang; |
| 332 | Pretraining Representations of Multi-modal Multi-query E-commerce Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper presents to represent MM search sessions by heterogeneous graph neural network (HGN). |
Xinyi Liu; Wanxian Guan; Lianyun Li; Hui Li; Chen Lin; Xubin Li; Si Chen; Jian Xu; Hongbo Deng; Bo Zheng; |
| 333 | Multi-task Hierarchical Classification for Disk Failure Prediction in Online Service Systems Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose MTHC (Multi-Task Hierarchical Classification) to enhance the performance of disk failure prediction for each task via multi-task learning. |
Yudong Liu; Hailan Yang; Pu Zhao; Minghua Ma; Chengwu Wen; Hongyu Zhang; Chuan Luo; Qingwei Lin; Chang Yi; Jiaojian Wang; Chenjian Zhang; Paul Wang; Yingnong Dang; Saravan Rajmohan; Dongmei Zhang; |
| 334 | Promotheus: An End-to-End Machine Learning Framework for Optimizing Markdown in Online Fashion E-commerce Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we introduce two novel end-to-end markdown management systems for optimising markdown at different stages of a retailer’s journey. |
Eleanor Loh; Jalaj Khandelwal; Brian Regan; Duncan A. Little; |
| 335 | Uncovering The Heterogeneous Effects of Preference Diversity on User Activeness: A Dynamic Mixture Model Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Unlike existing qualitative studies, we propose a universal mixture model with the capability of accurately fitting dynamic activeness curves while reflecting the heterogeneous patterns of preference diversity. |
Yunfei Lu; Peng Cui; Linyun Yu; Lei Li; Wenwu Zhu; |
| 336 | Retrieval-Based Gradient Boosting Decision Trees for Disease Risk Assessment Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a novel retrieval-based gradient boosting decision trees (RB-GBDT) model with a cross-sample extractor to mine cross-sample information while exploiting the superiority of GBDT of robustness, generalization and interpretability. |
Handong Ma; Jiahang Cao; Yuchen Fang; Weinan Zhang; Wenbo Sheng; Shaodian Zhang; Yong Yu; |
| 337 | An Online Multi-task Learning Framework for Google Feed Ads Auction Models Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we introduce a large scale online multi-task deep learning framework for modeling multiple feed ads auction prediction tasks on an industry-scale feed ads recommendation platform. |
Ning Ma; Mustafa Ispir; Yuan Li; Yongpeng Yang; Zhe Chen; Derek Zhiyuan Cheng; Lan Nie; Kishor Barman; |
| 338 | CS-RAD: Conditional Member Status Refinement and Ability Discovery for Social Network Applications Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we establish the consistency models among different member status and their abilities through analyzing member data and integrating domain knowledge. |
Yiming Ma; |
| 339 | Semantic Retrieval at Walmart Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a new technique to train the neural model at scale. |
Alessandro Magnani; Feng Liu; Suthee Chaidaroon; Sachin Yadav; Praveen Reddy Suram; Ajit Puthenputhussery; Sijie Chen; Min Xie; Anirudh Kashi; Tony Lee; Ciya Liao; |
| 340 | BE3R: BERT Based Early-Exit Using Expert Routing Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we propose a novel routing based early exit model called BE3R (BERT based Early-Exit using Expert Routing), where we learn to dynamically exit in the earlier layers without needing to traverse through the entire model. |
Sourab Mangrulkar; Ankith M S; Vivek Sembium; |
| 341 | Looper: An End-to-End ML Platform for Product Decisions Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To address shortcomings of prior platforms, we introduce general principles for and the architecture of an ML platform, Looper, with simple APIs for decision-making and feedback collection. |
Igor L. Markov; Hanson Wang; Nitya S. Kasturi; Shaun Singh; Mia R. Garrard; Yin Huang; Sze Wai Celeste Yuen; Sarah Tran; Zehui Wang; Igor Glotov; Tanvi Gupta; Peng Chen; Boshuang Huang; Xiaowen Xie; Michael Belkin; Sal Uryasev; Sam Howie; Eytan Bakshy; Norm Zhou; |
| 342 | Proactively Reducing The Hate Intensity of Online Posts Via Hate Speech Normalization Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We introduce NACL, a simple yet efficient hate speech normalization model that operates in three stages – first, it measures the hate intensity of the original sample; second, it identifies the hate span(s) within it; and finally, it reduces hate intensity by paraphrasing the hate spans. |
Sarah Masud; Manjot Bedi; Mohammad Aflah Khan; Md Shad Akhtar; Tanmoy Chakraborty; |
| 343 | CERAM: Coverage Expansion for Recommendations By Associating Discarded Models Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Here, our goal is to construct recommendation systems that expand the coverage of recommendations by effectively utilizing models which would otherwise be discarded.Another goal is to deploy such a recommendation system on real services and make practical use of it. |
Yoshiki Matsune; Kota Tsubouchi; Nobuhiko Nishio; |
| 344 | Packet Representation Learning for Traffic Classification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In the real world, although a packet may have different class labels for different tasks, the packet representation learned from one task can also help understand its complex packet patterns in other tasks, while existing works omit to leverage them. Taking advantage of this potential, in this work, we propose a novel framework to tackle the problem of packet representation learning for various traffic classification tasks. |
Xuying Meng; Yequan Wang; Runxin Ma; Haitong Luo; Xiang Li; Yujun Zhang; |
| 345 | Graph Neural Network Training and Data Tiering Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we provide a method to statistically analyze and identify more frequently accessed data ahead of GNN training. |
Seung Won Min; Kun Wu; Mert Hidayetoglu; Jinjun Xiong; Xiang Song; Wen-mei Hwu; |
| 346 | Towards Reliable Detection of Dielectric Hotspots in Thermal Images of The Underground Distribution Network Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper introduces a thermographic vision system to detect different types of hotspots on a variety of cable junctions commonly found in Hydro-Québec underground electrical distribution network. |
François Mirallès; Luc Cauchon; Marc-André Magnan; François Grégoire; Mouhamadou Makhtar Dione; Arnaud Zinflou; |
| 347 | Generating Examples from CLI Usage: Can Transformers Help? Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a practical system, which uses machine learning on large-scale telemetry data and documentation corpora, generating appropriate and complex examples that can be used to improve documentation. |
Roshanak Zilouchian Moghaddam; Spandan Garg; Colin B. Clement; Yevhen Mohylevskyy; Neel Sundaresan; |
| 348 | ASPIRE: Air Shipping Recommendation for E-commerce Products Via Causal Inference Framework Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a machine learning based framework to recommend air-shipping eligibility for products. |
Abhirup Mondal; Anirban Majumder; Vineet Chaoji; |
| 349 | DNA-Stabilized Silver Nanocluster Design Via Regularized Variational Autoencoders Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we present an approach to design AgN-DNAs by employing variational autoencoders (VAEs) as generative models. |
Fariha Moomtaheen; Matthew Killeen; James Oswald; Anna Gonzàlez-Rosell; Peter Mastracco; Alexander Gorovits; Stacy M. Copp; Petko Bogdanov; |
| 350 | GradMask: Gradient-Guided Token Masking for Textual Adversarial Example Detection Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We present GradMask, a simple adversarial example detection scheme for natural language processing (NLP) models. |
Han Cheol Moon; Shafiq Joty; Xu Chi; |
| 351 | Solar: Science of Entity Loss Attribution Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present an Attention based neural architecture for entity localization to accurately pinpoint the location of package loss in delivery network and bugs in erroneous programs. |
Anshuman Mourya; Prateek Sircar; Anirban Majumder; Deepak Gupta; |
| 352 | Pricing The Long Tail By Explainable Product Aggregation and Monotonic Bandits Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we provide a novel online learning algorithm for dynamic pricing that deals with non-stationary settings due to, e.g., the seasonality or adaptive competitors, and is very efficient in terms of the need for data thanks to assumptions such as, e.g., the monotonicity of the demand curve in the price that are customarily satisfied in long-tail markets. |
Marco Mussi; Gianmarco Genalti; Francesco Trovò; Alessandro Nuara; Nicola Gatti; Marcello Restelli; |
| 353 | Counterfactual Phenotyping with Censored Time-to-Events Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we present a latent variable approach to model heterogeneous treatment effects by proposing that an individual can belong to one of latent clusters with distinct response characteristics. |
Chirag Nagpal; Mononito Goswami; Keith Dufendach; Artur Dubrawski; |
| 354 | Crowdsourcing with Contextual Uncertainty Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present Theodon, a hierarchical non-parametric Bayesian model, developed and deployed at Meta, that captures both the prevalence of label categories and the accuracy of labelers as functions of the classifier score. |
Viet-An Nguyen; Peibei Shi; Jagdish Ramakrishnan; Narjes Torabi; Nimar S. Arora; Udi Weinsberg; Michael Tingley; |
| 355 | Amazon SageMaker Model Monitor: A System for Real-Time Insights Into Deployed Machine Learning Models Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present Amazon SageMaker Model Monitor, a fully managed service that continuously monitors the quality of machine learning models hosted on Amazon SageMaker. |
David Nigenda; Zohar Karnin; Muhammad Bilal Zafar; Raghu Ramesha; Alan Tan; Michele Donini; Krishnaram Kenthapadi; |
| 356 | Human-in-the-Loop Large-Scale Predictive Maintenance of Workstations Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We propose a human-in-the-loop PdM approach in which a machine learning system predicts future problems in sets of workstations (computers, laptops, and servers). |
Alexander Nikitin; Samuel Kaski; |
| 357 | GraphWorld: Fake Graphs Bring Real Insights for GNNs Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work we introduce GraphWorld, a novel methodology and system for benchmarking GNN models on an arbitrarily-large population ofsynthetic graphs for any conceivable GNN task. |
John Palowitch; Anton Tsitsulin; Brandon Mayer; Bryan Perozzi; |
| 358 | PinnerFormer: Sequence Modeling for User Representation at Pinterest Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Here we introduce PinnerFormer, a user representation trained to predict a user’s future long-term engagement using a sequential model of a user’s recent actions. |
Nikil Pancha; Andrew Zhai; Jure Leskovec; Charles Rosenberg; |
| 359 | Improving Relevance Modeling Via Heterogeneous Behavior Graph Learning in Bing Ads Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we study the novel problem of heterogeneous behavior graph learning to facilitate relevance modeling task. |
Bochen Pang; Chaozhuo Li; Yuming Liu; Jianxun Lian; Jianan Zhao; Hao Sun; Weiwei Deng; Xing Xie; Qi Zhang; |
| 360 | Temporal Multimodal Multivariate Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce temporal multimodal multivariate learning, a new family of decision making models that can indirectly learn and transfer online information from simultaneous observations of a probability distribution with more than one peak or more than one outcome variable from one time stage to another. |
Hyoshin Park; Justice Darko; Niharika Deshpande; Venktesh Pandey; Hui Su; Masahiro Ono; Dedrick Barkley; Larkin Folsom; Derek Posselt; Steve Chien; |
| 361 | Downscaling Earth System Models with Deep Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present a new method for downscaling climate simulations called GINE (Geospatial INformation Encoded statistical downscaling). |
Sungwon Park; Karandeep Singh; Arjun Nellikkattil; Elke Zeller; Tung Duong Mai; Meeyoung Cha; |
| 362 | DocLayNet: A Large Human-Annotated Dataset for Document-Layout Segmentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we presentDocLayNet, a new, publicly available, document-layout annotation dataset in COCO format. |
Birgit Pfitzmann; Christoph Auer; Michele Dolfi; Ahmed S. Nassar; Peter Staar; |
| 363 | Multi-objective Optimization of Notifications Using Offline Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we formulate the near-real-time notification decision problem as a Markov Decision Process where we optimize for multiple objectives in the rewards. |
Prakruthi Prabhakar; Yiping Yuan; Guangyu Yang; Wensheng Sun; Ajith Muralidharan; |
| 364 | What Makes Good Contrastive Learning on Small-Scale Wearable-based Tasks? Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To fill the gap, we aim to study contrastive learning on the wearable-based activity recognition task. |
Hangwei Qian; Tian Tian; Chunyan Miao; |
| 365 | Intelligent Request Strategy Design in Recommender System Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, previous attempts, including only non-adaptive strategies (e.g., insert requests uniformly), would eventually lead to resource overconsumption. To this end, we envision a new learning task of edge intelligence named Intelligent Request Strategy Design (IRSD). |
Xufeng Qian; Yue Xu; Fuyu Lv; Shengyu Zhang; Ziwen Jiang; Qingwen Liu; Xiaoyi Zeng; Tat-Seng Chua; Fei Wu; |
| 366 | Characterizing Covid Waves Via Spatio-Temporal Decomposition Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we develop a framework for analyzing patterns of a disease or pandemic such as Covid. |
Kevin Quinn; Evimaria Terzi; Mark Crovella; |
| 367 | NxtPost: User To Post Recommendations In Facebook Groups Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present NxtPost, a deployed user-to-post content based sequential recommender system for Facebook Groups. |
Kaushik Rangadurai; Yiqun Liu; Siddarth Malreddy; Xiaoyi Liu; Piyush Maheshwari; Vishwanath Sangale; Fedor Borisyuk; |
| 368 | Profiling Deep Learning Workloads at Scale Using Amazon SageMaker Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a new profiling tool that cross-correlates relevant system utilization metrics and framework operations. |
Nathalie Rauschmayr; Sami Kama; Muhyun Kim; Miyoung Choi; Krishnaram Kenthapadi; |
| 369 | Generative Adversarial Networks Enhanced Pre-training for Insufficient Electronic Health Records Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Directly using them to train sensitive medical models is very difficult to achieve satisfactory results. To overcome this problem, we propose a novel deep model learning method for insufficient EHR (Electronic Health Record) data modeling, namely GRACE, which stands GeneRative Adversarial networks enhanCed prE-training. |
Houxing Ren; Jingyuan Wang; Wayne Xin Zhao; |
| 370 | ChemicalX: A Deep Learning Library for Drug Pair Scoring Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we introduce ChemicalX, a PyTorch-based deep learning library designed for providing a range of state of the art models to solve the drug pair scoring task. |
Benedek Rozemberczki; Charles Tapley Hoyt; Anna Gogleva; Piotr Grabowski; Klas Karis; Andrej Lamov; Andriy Nikolov; Sebastian Nilsson; Michael Ughetto; Yu Wang; Tyler Derr; Bejamin M. Gyori; |
| 371 | Service Time Prediction for Delivery Tasks Via Spatial Meta-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose MetaSTP, a meta-learning based neural network model to predict the service time. |
Sijie Ruan; Cheng Long; Zhipeng Ma; Jie Bao; Tianfu He; Ruiyuan Li; Yiheng Chen; Shengnan Wu; Yu Zheng; |
| 372 | Reinforcement Learning in The Wild: Scalable RL Dispatching Algorithm Deployed in Ridehailing Marketplace Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this study, a scalable and real-time dispatching algorithm based on reinforcement learning is proposed and for the first time, is deployed in large scale. |
Soheil Sadeghi Eshkevari; Xiaocheng Tang; Zhiwei Qin; Jinhan Mei; Cheng Zhang; Qianying Meng; Jia Xu; |
| 373 | Semantic Aware Answer Sentence Selection Using Self-Learning Based Domain Adaptation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes SEDAN, an effective self-learning framework to adapt AS2 models for domain-specific applications. |
Rajdeep Sarkar; Sourav Dutta; Haytham Assem; Mihael Arcan; John McCrae; |
| 374 | Regional-Local Adversarially Learned One-Class Classifier Anomalous Sound Detection in Global Long-Term Space Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we propose a multi-pattern adversarial learning one-class classification framework, which allows us to use both the generator and the discriminator of an adversarial model for efficient ASD. |
Yu Sha; Shuiping Gou; Johannes Faber; Bo Liu; Wei Li; Stefan Schramm; Horst Stoecker; Thomas Steckenreiter; Domagoj Vnucec; Nadine Wetzstein; Andreas Widl; Kai Zhou; |
| 375 | Generalized Deep Mixed Models Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We introduce generalized deep mixed model (GDMix), a class of machine learning models for large-scale recommender systems that combines the power of deep neural networks and the efficiency of logistic regression. |
Jun Shi; Chengming Jiang; Aman Gupta; Mingzhou Zhou; Yunbo Ouyang; Qiang Charles Xiao; Qingquan Song; Yi (Alice) Wu; Haichao Wei; Huiji Gao; |
| 376 | Recommendation in Offline Stores: A Gamification Approach for Learning The Spatiotemporal Representation of Indoor Shopping Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this study, we propose a gamification approach wherein a real store is emulated in a pixel world and a recurrent convolutional network is trained to learn the spatiotemporal representation of offline shopping. |
Jongkyung Shin; Changhun Lee; Chiehyeon Lim; Yunmo Shin; Junseok Lim; |
| 377 | Septor: Seismic Depth Estimation Using Hierarchical Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper focuses on developing a machine learning model to accurately estimate the depth of arbitrary seismic events directly from seismograms. |
M Ashraf Siddiquee; Vinicius M. A. Souza; Glenn Eli Baker; Abdullah Mueen; |
| 378 | Seq2Event: Learning The Language of Soccer Using Transformer-based Match Event Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a more holistic approach, utilising Transformer or RNN components in the novel Seq2Event model, in which the next match event is predicted given prior match events and context. |
Ian Simpson; Ryan J. Beal; Duncan Locke; Timothy J. Norman; |
| 379 | Friend Recommendations with Self-Rescaling Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a simple but effective self-rescaling network (SSNet) to alleviate the scale distortion issue. |
Xiran Song; Jianxun Lian; Hong Huang; Mingqi Wu; Hai Jin; Xing Xie; |
| 380 | Counseling Summarization Using Mental Health Knowledge Guided Utterance Filtering Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, the aim is mental health counseling summarization to build upon domain knowledge and to help clinicians quickly glean meaning. |
Aseem Srivastava; Tharun Suresh; Sarah P. Lord; Md Shad Akhtar; Tanmoy Chakraborty; |
| 381 | Type Linking for Query Understanding and Semantic Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present techniques that we designed in order to address challenges with the type dictionary, incompatibilities in scoring between the term-based and vector-based methods as well as over-segmentation issues in Thai, Chinese, and Japanese. |
Giorgos Stoilos; Nikos Papasarantopoulos; Pavlos Vougiouklis; Patrik Bansky; |
| 382 | Few-shot Learning for Trajectory-based Mobile Game Cheating Detection Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Even worse, in practice, the cheating programs are quickly updated, leading to the label scarcity for novel cheating patterns. To handle such issues, we in this paper introduce a mobile game cheating detection framework, namely FCDGame, to detect the cheats under the few-shot learning framework. |
Yueyang Su; Di Yao; Xiaokai Chu; Wenbin Li; Jingping Bi; Shiwei Zhao; Runze Wu; Shize Zhang; Jianrong Tao; Hao Deng; |
| 383 | Optimizing Long-Term Efficiency and Fairness in Ride-Hailing Via Joint Order Dispatching and Driver Repositioning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Thus, in this paper, we aim to exploit joint order dispatching and driver repositioning to optimize both the long-term efficiency and fairness for ride-hailing platforms. |
Jiahui Sun; Haiming Jin; Zhaoxing Yang; Lu Su; Xinbing Wang; |
| 384 | CognitionNet: A Collaborative Neural Network for Play Style Discovery in Online Skill Gaming Platform Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this effect, we focus on discovery of the "game behaviours" as micro-patterns formed by continuous sequence of games and the persistent "play styles" of the players’ as a sequence of such sequences on an online skill gaming platform for Rummy. |
Rukma Talwadker; Surajit Chakrabarty; Aditya Pareek; Tridib Mukherjee; Deepak Saini; |
| 385 | 4SDrug: Symptom-based Set-to-set Small and Safe Drug Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To deal with the challenges above, in this paper, we propose a novel framework of Symptom-based Set-to-set Small and Safe drug recommendation (4SDrug). |
Yanchao Tan; Chengjun Kong; Leisheng Yu; Pan Li; Chaochao Chen; Xiaolin Zheng; Vicki S. Hertzberg; Carl Yang; |
| 386 | What Is The Most Effective Intervention to Increase Job Retention for This Disabled Worker? Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This paper proposes a representation learning method for recommending personalized interventions that can generate a maximum increase in job retention time for workers with disability. |
Ha Xuan Tran; Thuc Duy Le; Jiuyong Li; Lin Liu; Jixue Liu; Yanchang Zhao; Tony Waters; |
| 387 | Reinforcement Learning-based Placement of Charging Stations in Urban Road Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We design a novel Deep Reinforcement Learning approach to solve the charging station placement problem (PCRL). |
Leonie von Wahl; Nicolas Tempelmeier; Ashutosh Sao; Elena Demidova; |
| 388 | A Graph Learning Based Framework for Billion-Scale Offline User Identification Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we elaborately design an offline identification framework considering two aspects. |
Daixin Wang; Zujian Weng; Zhengwei Wu; Zhiqiang Zhang; Peng Cui; Hongwei Zhao; Jun Zhou; |
| 389 | Learning Supplementary NLP Features for CTR Prediction in Sponsored Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: For this purpose, we introduce a simple and general joint-training framework for fine-tuning of language models, combined with the already existing features in CTR prediction baseline, to extract supplementary knowledge for NLP feature. |
Dong Wang; Shaoguang Yan; Yunqing Xia; Kavé Salamatian; Weiwei Deng; Qi Zhang; |
| 390 | ROI-Constrained Bidding Via Curriculum-Guided Bayesian Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we specialize in ROI-Constrained Bidding in non-stationary markets. |
Haozhe Wang; Chao Du; Panyan Fang; Shuo Yuan; Xuming He; Liang Wang; Bo Zheng; |
| 391 | NENYA: Cascade Reinforcement Learning for Cost-Aware Failure Mitigation at Microsoft 365 Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: As information is not fully shared across those two stages, important factors such as mitigation costs and states of instances are often ignored in one of those two stages. To address these issues, we propose NENYA, an end-to-end mitigation solution for a large-scale database system powered by a novel cascade reinforcement learning model. |
Lu Wang; Pu Zhao; Chao Du; Chuan Luo; Mengna Su; Fangkai Yang; Yudong Liu; Qingwei Lin; Min Wang; Yingnong Dang; Hongyu Zhang; Saravan Rajmohan; Dongmei Zhang; |
| 392 | Learning to Discover Causes of Traffic Congestion with Limited Labeled Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Hence, we aim to discover the known and unknown causes of traffic congestion in a systematic way. |
Mudan Wang; Huan Yan; Hongjie Sui; Fan Zuo; Yue Liu; Yong Li; |
| 393 | RT-VeD: Real-Time VoI Detection on Edge Nodes with An Adaptive Model Selection Framework Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, resource-constrained edge devices are not competent for dynamic traffic loads with resource-intensive video analysis models. To address this challenge, we propose RT-VeD, a real-time VoI detection system based on the limited resources of edge nodes. |
Shuai Wang; Junke Lu; Baoshen Guo; Zheng Dong; |
| 394 | Representative Routes Discovery from Massive Trajectories Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we study how to find the k most representative routes over large scale trajectory data, which is a fundamental operation that benefits various real-world applications, such as traffic monitoring and public transportation planning. |
Tingting Wang; Shixun Huang; Zhifeng Bao; J. Shane Culpepper; Reza Arablouei; |
| 395 | CONFLUX: A Request-level Fusion Framework for Impression Allocation Via Cascade Distillation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper proposes CONFLUX, a fusion framework located at the confluence of the parallel GD and RTB markets. |
XiaoYu Wang; Bin Tan; Yonghui Guo; Tao Yang; Dongbo Huang; Lan Xu; Nikolaos M. Freris; Hao Zhou; Xiang-Yang Li; |
| 396 | Fed-LTD: Towards Cross-Platform Ride Hailing Via Federated Learning to Dispatch Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we advocate federated order dispatching for cross-platform ride hailing, where multiple platforms collaboratively make dispatching decisions without sharing their local data. |
Yansheng Wang; Yongxin Tong; Zimu Zhou; Ziyao Ren; Yi Xu; Guobin Wu; Weifeng Lv; |
| 397 | CausalInt: Causal Inspired Intervention for Multi-Scenario Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we show it is possible to selectively utilize the information from different scenarios to construct the scenario-aware estimators in a unified model. |
Yichao Wang; Huifeng Guo; Bo Chen; Weiwen Liu; Zhirong Liu; Qi Zhang; Zhicheng He; Hongkun Zheng; Weiwei Yao; Muyu Zhang; Zhenhua Dong; Ruiming Tang; |
| 398 | Surrogate for Long-Term User Experience in Recommender Systems Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: These long term outcomes however are much harder to optimize due to the sparsity in observing these events and low signal-to-noise ratio (weak connection) between these long-term outcomes and a single recommendation. To address these challenges, we propose to establish the association between these long-term outcomes and a set of more immediate term user behavior signals that can serve as surrogates for optimization. |
Yuyan Wang; Mohit Sharma; Can Xu; Sriraj Badam; Qian Sun; Lee Richardson; Lisa Chung; Ed H. Chi; Minmin Chen; |
| 399 | FederatedScope-GNN: Towards A Unified, Comprehensive and Efficient Package for Federated Graph Learning Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Motivated by such strong demand, in this paper, we first discuss the challenges in creating an easy-to-use FGL package and accordingly present our implemented package FederatedScope-GNN (FS-G), which provides (1) a unified view for modularizing and expressing FGL algorithms; (2) comprehensive DataZoo and ModelZoo for out-of-the-box FGL capability; (3) an efficient model auto-tuning component; and (4) off-the-shelf privacy attack and defense abilities. |
Zhen Wang; Weirui Kuang; Yuexiang Xie; Liuyi Yao; Yaliang Li; Bolin Ding; Jingren Zhou; |
| 400 | Connecting The Hosts: Street-Level IP Geolocation with Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Motivated by the limitations in existing works, we propose a novel framework named GraphGeo, which provides a complete processing methodology for street-level IP geolocation with the application of graph neural networks. |
Zhiyuan Wang; Fan Zhou; Wenxuan Zeng; Goce Trajcevski; Chunjing Xiao; Yong Wang; Kai Chen; |
| 401 | Interpretability, Then What? Editing Machine Learning Models to Reflect Human Knowledge and Values Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In a collaboration between ML and human-computer interaction researchers, physicians, and data scientists, we develop GAM Changer, the first interactive system to help domain experts and data scientists easily and responsibly edit Generalized Additive Models (GAMs) and fix problematic patterns. |
Zijie J. Wang; Alex Kale; Harsha Nori; Peter Stella; Mark E. Nunnally; Duen Horng Chau; Mihaela Vorvoreanu; Jennifer Wortman Vaughan; Rich Caruana; |
| 402 | Graph2Route: A Dynamic Spatial-Temporal Graph Neural Network for Pick-up and Delivery Route Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Therefore, to meet the rising calling for route prediction models that can capture workers’ future routing behaviors, in this paper, we formulate the Pick-up and Delivery Route Prediction task (PDRP task for short) from the graph perspective for the first time, then propose a dynamic spatial-temporal graph-based model, named Graph2Route. |
Haomin Wen; Youfang Lin; Xiaowei Mao; Fan Wu; Yiji Zhao; Haochen Wang; Jianbin Zheng; Lixia Wu; Haoyuan Hu; Huaiyu Wan; |
| 403 | Graph Neural Networks for Multimodal Single-Cell Data Integration Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To address these challenges and correspondingly facilitate multimodal single-cell data analyses, three key tasks have been introduced: Modality prediction, Modality matching andJoint embedding. In this work, we present a general Graph Neural Network framework scMoGNN to tackle these three tasks and show that scMoGNN demonstrates superior results in all three tasks compared with the state-of-the-art and conventional approaches. |
Hongzhi Wen; Jiayuan Ding; Wei Jin; Yiqi Wang; Yuying Xie; Jiliang Tang; |
| 404 | FedAttack: Effective and Covert Poisoning Attack on Federated Recommendation Via Hard Sampling Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a simple yet effective and covert poisoning attack method on federated recommendation, named FedAttack. |
Chuhan Wu; Fangzhao Wu; Tao Qi; Yongfeng Huang; Xing Xie; |
| 405 | Interpretable Personalized Experimentation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a scalable, interpretable personalized experimentation system, implemented and deployed in production at Meta. |
Han Wu; Sarah Tan; Weiwei Li; Mia Garrard; Adam Obeng; Drew Dimmery; Shaun Singh; Hanson Wang; Daniel Jiang; Eytan Bakshy; |
| 406 | Learning Large-scale Subsurface Simulations with A Hybrid Graph Network Simulator Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Here we introduce Hybrid Graph Network Simulator (HGNS), which is a data-driven surrogate model for learning reservoir simulations of 3D subsurface fluid flows. |
Tailin Wu; Qinchen Wang; Yinan Zhang; Rex Ying; Kaidi Cao; Rok Sosic; Ridwan Jalali; Hassan Hamam; Marko Maucec; Jure Leskovec; |
| 407 | A Framework for Multi-stage Bonus Allocation in Meal Delivery Platform Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To make better use of the funds, in this work, we propose a framework to deal with the multi-stage bonus allocation problem for a meal delivery platform. |
Zhuolin Wu; Li Wang; Fangsheng Huang; Linjun Zhou; Yu Song; Chengpeng Ye; Pengyu Nie; Hao Ren; Jinghua Hao; Renqing He; Zhizhao Sun; |
| 408 | Multi Armed Bandit Vs. A/B Tests in E-commence – Confidence Interval and Hypothesis Test Power Perspectives Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Based on the theoretical analysis, we propose two new MAB algorithms that combine the strengths of traditional MAB and A/B together, with higher (or equal) test power and higher (or equal) expected rewards than A/B testing under certain common conditions in e-commerce. |
Ding Xiang; Rebecca West; Jiaqi Wang; Xiquan Cui; Jinzhou Huang; |
| 409 | Training Large-Scale News Recommenders with Pretrained Language Models in The Loop Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a novel framework, SpeedyFeed, which efficiently trains PLMs-based news recommenders of superior quality. |
Shitao Xiao; Zheng Liu; Yingxia Shao; Tao Di; Bhuvan Middha; Fangzhao Wu; Xing Xie; |
| 410 | Contrastive Cross-domain Recommendation in Matching Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose a novel Contrastive Cross-Domain Recommendation (CCDR) framework for CDR in matching. |
Ruobing Xie; Qi Liu; Liangdong Wang; Shukai Liu; Bo Zhang; Leyu Lin; |
| 411 | G2NET: A General Geography-Aware Representation Network for Hotel Search Ranking Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, we propose a General Geography-aware representation NETwork (G2NET for short) to better represent geography information of location entities so as to optimize the hotel search ranking. |
Jia Xu; Fei Xiong; Zulong Chen; Mingyuan Tao; Liangyue Li; Quan Lu; |
| 412 | COSSUM: Towards Conversation-Oriented Structured Summarization for Automatic Medical Insurance Assessment Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: With the purpose of helping save human labor, we propose the task of conversation-oriented structured summarization which aims to automatically produce the desired structured summary from a conversation automatically. |
Sheng Xu; Xiaojun Wan; Sen Hu; Mengdi Zhou; Teng Xu; Hongbin Wang; Haitao Mi; |
| 413 | Mixture of Virtual-Kernel Experts for Multi-Objective User Profile Modeling Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper introduces a novel multi-task model called Mixture of Virtual-Kernel Experts (MVKE) to learn user preferences on various actions and topics unitedly. |
Zhenhui Xu; Meng Zhao; Liqun Liu; Lei Xiao; Xiaopeng Zhang; Bifeng Zhang; |
| 414 | Perioperative Predictions with Interpretable Latent Representation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We proposeclinical variational autoencoder (cVAE), a deep latent variable model that addresses the challenges of surgical applications through two salient features. (1) To overcome performance limitations of traditional VAE, it isprediction-guided with explicit expression of predicted outcome in the latent representation. (2) Itdisentangles the latent space so that it can be interpreted in a clinically meaningful fashion. |
Bing Xue; York Jiao; Thomas Kannampallil; Bradley Fritz; Christopher King; Joanna Abraham; Michael Avidan; Chenyang Lu; |
| 415 | Multiwave COVID-19 Prediction from Social Awareness Using Web Search and Mobility Data Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Therefore, to predict the multiwave pandemic, we propose a Social Awareness-Based Graph Neural Network (SAB-GNN) that considers the decay of symptom-related web search frequency to capture the changes in public awareness across multiple waves. |
Jiawei Xue; Takahiro Yabe; Kota Tsubouchi; Jianzhu Ma; Satish Ukkusuri; |
| 416 | A Meta Reinforcement Learning Approach for Predictive Autoscaling in The Cloud Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: To this end, we propose an end-to-end predictive meta model-based RL algorithm, aiming to optimally allocate resource to maintain a stable CPU utilization level, which incorporates a specially-designed deep periodic workload prediction model as the input and embeds the Neural Process [11, 16] to guide the learning of the optimal scaling actions over numerous application services in the Cloud. |
Siqiao Xue; Chao Qu; Xiaoming Shi; Cong Liao; Shiyi Zhu; Xiaoyu Tan; Lintao Ma; Shiyu Wang; Shijun Wang; Yun Hu; Lei Lei; Yangfei Zheng; Jianguo Li; James Zhang; |
| 417 | Scale Calibration of Deep Ranking Models Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We rigorously show that, both theoretically and empirically, this property leads to training instability that may cause severe practical issues. In this paper, we study how to perform scale calibration of deep ranking models to address the above concerns. |
Le Yan; Zhen Qin; Xuanhui Wang; Michael Bendersky; Marc Najork; |
| 418 | CMMD: Cross-Metric Multi-Dimensional Root Cause Analysis Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, we propose a cross-metric multi-dimensional root cause analysis method, named CMMD, which consists of two key components: 1) relationship modeling, which utilizes graph neural network (GNN) to model the unknown complex calculation among metrics and aggregation function among dimensions from historical data; 2) root cause localization, which adopts the genetic algorithm to efficiently and effectively dive into the raw data and localize the abnormal dimension(s) once the KPI anomalies are detected. |
Shifu Yan; Caihua Shan; Wenyi Yang; Bixiong Xu; Dongsheng Li; Lili Qiu; Jie Tong; Qi Zhang; |
| 419 | DuARE: Automatic Road Extraction with Aerial Images and Trajectory Data at Baidu Maps Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present an automatic road extraction solution named DuARE, which is designed to exploit the multimodal knowledge for underlying road extraction in a fully automatic manner. |
Jianzhong Yang; Xiaoqing Ye; Bin Wu; Yanlei Gu; Ziyu Wang; Deguo Xia; Jizhou Huang; |
| 420 | TAG: Toward Accurate Social Media Content Tagging with A Concept Graph Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present TAG, a high-quality concept matching dataset consisting of 10,000 labeled pairs of fine-grained concepts and web-styled natural language sentences, mined from open-domain social media content. |
Jiuding Yang; Weidong Guo; Bang Liu; Yakun Yu; Chaoyue Wang; Jinwen Luo; Linglong Kong; Di Niu; Zhen Wen; |
| 421 | CausalMTA: Eliminating The User Confounding Bias for Causal Multi-touch Attribution Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we define the causal MTA task and propose CausalMTA to solve this problem. |
Di Yao; Chang Gong; Lei Zhang; Sheng Chen; Jingping Bi; |
| 422 | Device-cloud Collaborative Recommendation Via Meta Controller Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: However, such a design is inflexible when user interests dramatically change: the on-device model is stuck by the limited item cache while the cloud-based recommendation based on the large item pool do not respond without the new re-fresh feedback. To overcome this issue, we propose a meta controller to dynamically manage the collaboration between the on-device recommender and the cloud-based recommender, and introduce a novel efficient sample construction from the causal perspective to solve the dataset absence issue of meta controller. |
Jiangchao Yao; Feng Wang; Xichen Ding; Shaohu Chen; Bo Han; Jingren Zhou; Hongxia Yang; |
| 423 | ReprBERT: Distilling BERT to An Efficient Representation-Based Relevance Model for E-Commerce Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Recently BERT has achieved significant progress on many NLP tasks including text matching, and it is of great value but also big challenge to deploy BERT to the e-commerce relevance task. To realize this goal, we propose ReprBERT, which has the advantages of both excellent performance and low latency, by distilling the interaction-based BERT model to a representation-based architecture. |
Shaowei Yao; Jiwei Tan; Xi Chen; Juhao Zhang; Xiaoyi Zeng; Keping Yang; |
| 424 | Multilingual Taxonomic Web Page Classification for Contextual Targeting at Yahoo Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we use multilingual Transformer-based transfer learning models to classify web pages in five high-impact languages. |
Eric Ye; Xiao Bai; Neil O’Hare; Eliyar Asgarieh; Kapil Thadani; Francisco Perez-Sorrosal; Sujyothi Adiga; |
| 425 | A Stochastic Shortest Path Algorithm for Optimizing Spaced Repetition Scheduling Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Based on the model, we design a spaced repetition scheduler guaranteed to minimize the review cost by a stochastic shortest path algorithm. |
Junyao Ye; Jingyong Su; Yilong Cao; |
| 426 | Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graph Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Inspired by the embedding compression methods developed for natural language processing (NLP) tasks, we develop a node embedding compression method where each node is compactly represented with a bit vector instead of a floating-point vector. |
Chin-Chia Michael Yeh; Mengting Gu; Yan Zheng; Huiyuan Chen; Javid Ebrahimi; Zhongfang Zhuang; Junpeng Wang; Liang Wang; Wei Zhang; |
| 427 | Predicting Age-Related Macular Degeneration Progression with Contrastive Attention and Time-Aware LSTM Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we propose a C ontrastive-A ttention-based T ime-aware L ong S hort-T erm M emory network (CAT-LSTM ) to predict AMD progression. |
Changchang Yin; Sayoko E. Moroi; Ping Zhang; |
| 428 | Spatio-Temporal Vehicle Trajectory Recovery on Road Network Based on Traffic Camera Video Data Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To deal with these challenges, we design a novel system to recover the vehicle trajectory with the granularity of the road intersection. In this system, we propose an iterative framework to jointly optimize the vehicle re-identification and trajectory recovery tasks. |
Fudan Yu; Wenxuan Ao; Huan Yan; Guozhen Zhang; Wei Wu; Yong Li; |
| 429 | XDAI: A Tuning-free Framework for Exploiting Pre-trained Language Models in Knowledge Grounded Dialogue Generation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: However, there remain challenges for individual developers to create a knowledge-grounded dialogue system upon such big models because of the expensive cost of collecting the knowledge resources for supporting the system as well as tuning these large models for the task. To tackle these obstacles, we propose XDAI, a knowledge-grounded dialogue system that is equipped with the prompt-aware tuning-free PLM exploitation and supported by the ready-to-use open-domain external knowledge resources plus the easy-to-change domain-specific mechanism. |
Jifan Yu; Xiaohan Zhang; Yifan Xu; Xuanyu Lei; Xinyu Guan; Jing Zhang; Lei Hou; Juanzi Li; Jie Tang; |
| 430 | CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We introduce CommerceMM – a multimodal model capable of providing a diverse and granular understanding of commerce topics associated to the given piece of content (image, text, image+text), and having the capability to generalize to a wide range of tasks, including Multimodal Categorization, Image-Text Retrieval, Query-to-Product Retrieval, Image-to-Product Retrieval, etc. |
Licheng Yu; Jun Chen; Animesh Sinha; Mengjiao Wang; Yu Chen; Tamara L. Berg; Ning Zhang; |
| 431 | EGM: Enhanced Graph-based Model for Large-scale Video Advertisement Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we enhance the graph-based model through sub-path embedding to differentiate similar videos. |
Tan Yu; Jie Liu; Yi Yang; Yi Li; Hongliang Fei; Ping Li; |
| 432 | Multi-task Envisioning Transformer-based Autoencoder for Corporate Credit Rating Migration Early Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we consider the corporate credit rating migration early prediction problem, which predicts the credit rating of an issuer will be upgraded, unchanged, or downgraded after 12 months based on its latest financial reporting information at the time. |
Han Yue; Steve Xia; Hongfu Liu; |
| 433 | AutoShard: Automated Embedding Table Sharding for Recommender Systems Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this work, we introduce our novel practice in Meta, namely AutoShard, which uses a neural cost model to directly predict the multi-table costs and leverages deep reinforcement learning to solve the partition problem. |
Daochen Zha; Louis Feng; Bhargav Bhushanam; Dhruv Choudhary; Jade Nie; Yuandong Tian; Jay Chae; Yinbin Ma; Arun Kejariwal; Xia Hu; |
| 434 | Deconfounding Duration Bias in Watch-time Prediction for Video Recommendation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To remove the undesired bias but leverage the natural effect, we propose a Duration-Deconfounded Quantile-based (D2Q) watch-time prediction framework, which allows for scalability to perform on industry production systems. |
Ruohan Zhan; Changhua Pei; Qiang Su; Jianfeng Wen; Xueliang Wang; Guanyu Mu; Dong Zheng; Peng Jiang; Kun Gai; |
| 435 | Data-Driven Oracle Bone Rejoining: A Dataset and Practical Self-Supervised Learning Scheme Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, we collect a real-world dataset for rejoining Oracle Bone fragments, namely OB-Rejoin, which consists of 998 OB rubbing images that suffer from low quality image problems, due to intrinsic underground eroding over time and extrinsic imaging conditions in the past. |
Chongsheng Zhang; Bin Wang; Ke Chen; Ruixing Zong; Bo-feng Mo; Yi Men; George Almpanidis; Shanxiong Chen; Xiangliang Zhang; |
| 436 | Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we present a novel representation learning framework Uni-Retriever developed for Bing Search, which unifies two different training modes knowledge distillation and contrastive learning to realize both required objectives. |
Jianjin Zhang; Zheng Liu; Weihao Han; Shitao Xiao; Ruicheng Zheng; Yingxia Shao; Hao Sun; Hanqing Zhu; Premkumar Srinivasan; Weiwei Deng; Qi Zhang; Xing Xie; |
| 437 | Felicitas: Federated Learning in Distributed Cross Device Collaborative Frameworks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Felicitas is a distributed cross-device Federated Learning (FL) framework to solve the industrial difficulties of FL in large-scale device deployment scenarios. |
Qi Zhang; Tiancheng Wu; Peichen Zhou; Shan Zhou; Yuan Yang; Xiulang Jin; |
| 438 | Multi-Task Fusion Via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a conservative offline policy estimator (Conservative-OPEstimator) to test our model offline. |
Qihua Zhang; Junning Liu; Yuzhuo Dai; Yiyan Qi; Yifan Yuan; Kunlun Zheng; Fan Huang; Xianfeng Tan; |
| 439 | Adaptive Multi-view Rule Discovery for Weakly-Supervised Compatible Products Prediction Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study the problem of discovering effective labeling rules that can enable weakly-supervised product compatibility prediction. |
Rongzhi Zhang; Rebecca West; Xiquan Cui; Chao Zhang; |
| 440 | Sparx: Distributed Outlier Detection at Scale Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This area, however, is not only understudied but also short of public-domain implementations for practical use. This paper aims to fill this gap: We design Sparx, a data-parallel OD algorithm suitable for shared-nothing infrastructures, which we specifically implement in Apache Spark. |
Sean Zhang; Varun Ursekar; Leman Akoglu; |
| 441 | CAT: Beyond Efficient Transformer for Content-Aware Anomaly Detection in Event Sequences Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To this end, in this paper, we propose a self-attentive encoder-decoder transformer framework, Content-Aware Transformer CAT, for anomaly detection in event sequences. |
Shengming Zhang; Yanchi Liu; Xuchao Zhang; Wei Cheng; Haifeng Chen; Hui Xiong; |
| 442 | Medical Symptom Detection in Intelligent Pre-Consultation Using Bi-directional Hard-Negative Noise Contrastive Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we formulate symptom detection as a retrieval problem and propose a bi-directional hard-negative enforced noise contrastive estimation method (Bi-hardNCE) to tackle the symptom detection problem. |
Shiwei Zhang; Jichao Sun; Yu Huang; Xueqi Ding; Yefeng Zheng; |
| 443 | Graph Attention Multi-Layer Perceptron Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: Although some scalable GNNs are proposed for large-scale graphs, they adopt a fixed K-hop neighborhood for each node, thus facing the over-smoothing issue when adopting large propagation depths for nodes within sparse regions. To tackle the above issue, we propose a new GNN architecture — Graph Attention Multi-Layer Perceptron (GAMLP), which can capture the underlying correlations between different scales of graph knowledge. |
Wentao Zhang; Ziqi Yin; Zeang Sheng; Yang Li; Wen Ouyang; Xiaosen Li; Yangyu Tao; Zhi Yang; Bin Cui; |
| 444 | JiuZhang: A Chinese Pre-trained Language Model for Mathematical Problem Understanding Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper aims to advance the mathematical intelligence of machines by presenting the first Chinese mathematical pre-trained language model (PLM) for effectively understanding and representing mathematical problems. |
Wayne Xin Zhao; Kun Zhou; Zheng Gong; Beichen Zhang; Yuanhang Zhou; Jing Sha; Zhigang Chen; Shijin Wang; Cong Liu; Ji-Rong Wen; |
| 445 | Distributed Hybrid CPU and GPU Training for Graph Neural Networks on Billion-Scale Heterogeneous Graphs Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In these domains, the graphs are typically large and heterogeneous, containing many millions or billions of vertices and edges of different types. To tackle this challenge, we develop DistDGLv2, a system that extends DistDGL for training GNNs on massive heterogeneous graphs in a mini-batch fashion, using distributed hybrid CPU/GPU training. |
Da Zheng; Xiang Song; Chengru Yang; Dominique LaSalle; George Karypis; |
| 446 | DDR: Dialogue Based Doctor Recommendation for Online Medical Service Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Intuitively, it is a crucial step to recommend suitable doctor candidates for patients, especially with suffering the severe cold-start challenge of patients due to the limited historical records and insufficient description of patient condition. Along this line, in this paper, we propose a novel Dialogue based Doctor Recommendation (DDR) model, which comprehensively integrates three types of information in modeling, including the profile and chief complaint from patients, the historical records of doctors and the patient-doctor dialogue. |
Zhi Zheng; Zhaopeng Qiu; Hui Xiong; Xian Wu; Tong Xu; Enhong Chen; Xiangyu Zhao; |
| 447 | Dynamic Graph Segmentation for Deep Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We present Deep network Dynamic Graph Partitioning (DDGP), a novel algorithm for optimizing the division of large graphs for mixture of expert graph neural networks. |
Johan Kok Zhi Kang; Suwei Yang; Suriya Venkatesan; Sien Yi Tan; Feng Cheng; Bingsheng He; |
| 448 | DESCN: Deep Entire Space Cross Networks for Individual Treatment Effect Estimation Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This paper proposes Deep Entire Space Cross Networks (DESCN) to model treatment effects from an end-to-end perspective. |
Kailiang Zhong; Fengtong Xiao; Yan Ren; Yaorong Liang; Wenqing Yao; Xiaofeng Yang; Ling Cen; |
| 449 | Combo-Fashion: Fashion Clothes Matching CTR Prediction with Item History Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this work, we tackle this problem by designing a novel algorithm called Combo-Fashion, which extracts the matching effect by introducing the matching history of the combo item with two cascaded modules: (i) Matching Search Module (MSM) seeks the popular combo items and undesirable ones as a positive set and a negative set, respectively; (ii) Matching Prediction Module (MPM) models the precise relationship between the candidate combo item and the positive/negative set by an attention-based deep model. |
Chenxu Zhu; Peng Du; Weinan Zhang; Yong Yu; Yang Cao; |
| 450 | User-tag Profile Modeling in Recommendation System Via Contrast Weighted Tag Masking Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: This leads to data discrepancy between the training and testing samples. To address such an issue, we attempt a novel Random Masking Model (RMM) to remain only one tag at the training time by masking. |
Chenxu Zhu; Peng Du; Xianghui Zhu; Weinan Zhang; Yong Yu; Yang Cao; |
| 451 | Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networks Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: This presents a serious problem, because a vast number of zeros deviate from the Gaussian assumption underlying the deterministic deep learning models. To address this issue, we design a Spatial-Temporal Zero-Inflated Negative Binomial Graph Neural Network (STZINB-GNN) to quantify the uncertainty of the sparse travel demand. |
Dingyi Zhuang; Shenhao Wang; Haris Koutsopoulos; Jinhua Zhao; |
| 452 | RBG: Hierarchically Solving Large-Scale Routing Problems in Logistic Systems Via Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper we present a novel Rewriting-by-Generating (RBG) framework which solves large-scale VRPs hierarchically. |
Zefang Zong; Hansen Wang; Jingwei Wang; Meng Zheng; Yong Li; |
| 453 | Effective Social Network-Based Allocation of COVID-19 Vaccines Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We study allocation of COVID-19 vaccines to individuals based on the structural properties of their underlying social contact network. |
Jiangzhuo Chen; Stefan Hoops; Achla Marathe; Henning Mortveit; Bryan Lewis; Srinivasan Venkatramanan; Arash Haddadan; Parantapa Bhattacharya; Abhijin Adiga; Anil Vullikanti; Aravind Srinivasan; Mandy L. Wilson; Gal Ehrlich; Maier Fenster; Stephen Eubank; Christopher Barrett; Madhav Marathe; |
| 454 | Reinforcement Learning Enhances The Experts: Large-scale COVID-19 Vaccine Allocation with Multi-factor Contact Network Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we propose a reinforcement learning enhanced experts method. |
Qianyue Hao; Wenzhen Huang; Fengli Xu; Kun Tang; Yong Li; |
| 455 | Scalable Online Disease Diagnosis Via Multi-Model-Fused Actor-Critic Reinforcement Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: They perform well when the feature space is small, that is, the number of symptoms and diagnosable disease categories is limited, but they frequently fail in assignments with a large number of features. To address this challenge, we propose a Multi-Model-Fused Actor-Critic (MMF-AC) RL framework that consists of a generative actor network and a diagnostic critic network. |
Weijie He; Ting Chen; |
| 456 | User Engagement in Mobile Health Applications Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: We propose a framework to study user engagement with mobile health, focusing on healthcare workers and digital health apps designed to support them in resource-poor settings. |
Babaniyi Yusuf Olaniyi; Ana Fernández del Río; África Periáñez; Lauren Bellhouse; |
| 457 | Automatic Phenotyping By A Seed-guided Topic Model Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: We present a seed-guided Bayesian topic model called MixEHR-Seed with 3 contributions: (1) for each phenotype, we infer a dual-form of topic distribution: a seed-topic distribution over a small set of key EHR codes and a regular topic distribution over the entire EHR vocabulary; (2) we model age-dependent disease progression as Markovian dynamic topic priors; (3) we infer seed-guided multi-modal topics over distinct EHR data types. |
Ziyang Song; Yuanyi Hu; Aman Verma; David L. Buckeridge; Yue Li; |
| 458 | MolSearch: Search-based Multi-objective Molecular Generation and Property Optimization Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Towards real-world applications, however, efficient generation of molecules that satisfy multiple property requirements simultaneously remains a key challenge. In this paper, we tackle this challenge using a search-based approach and propose a simple yet effective framework called MolSearch for multi-objective molecular generation (optimization). |
Mengying Sun; Jing Xing; Han Meng; Huijun Wang; Bin Chen; Jiayu Zhou; |
| 459 | Dynamic Network Anomaly Modeling of Cell-Phone Call Detail Records for Infectious Disease Surveillance Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: In this paper, we develop the necessary models to conduct population-level infectious disease surveillance by using cell-phone metadata individually linked with health outcomes. |
Carl Yang; Hongwen Song; Mingyue Tang; Leon Danon; Ymir Vigfusson; |
| 460 | Data-Efficient Brain Connectome Analysis Via Multi-Task Meta-Learning Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: Specifically, we propose to meta-train the model on datasets of large sample sizes and transfer the knowledge to small datasets. |
Yi Yang; Yanqiao Zhu; Hejie Cui; Xuan Kan; Lifang He; Ying Guo; Carl Yang; |
| 461 | Activity Trajectory Generation Via Modeling Spatiotemporal Dynamics Related Papers Related Patents Related Grants Related Orgs Related Experts Related Code View Highlight: In this paper, we present a novel framework based on generative adversarial imitation learning, to generate artificial activity trajectories that retain both the fidelity and utility of the real-world data. |
Yuan Yuan; Jingtao Ding; Huandong Wang; Depeng Jin; Yong Li; |
| 462 | Medical Dialogue Response Generation with Pivotal Information Recalling Related Papers Related Patents Related Grants Related Orgs Related Experts View Highlight: To mitigate this problem, we propose a medical response generation model with Pivotal Information Recalling (MedPIR), which is built on two components, i.e., knowledge-aware dialogue graph encoder and recall-enhanced generator. |
Yu Zhao; Yunxin Li; Yuxiang Wu; Baotian Hu; Qingcai Chen; Xiaolong Wang; Yuxin Ding; Min Zhang; |