Paper Digest: KDD 2024 Papers & Highlights
To search or review papers within KDD-2024 related to a specific topic, please use the search by venue and review by venue services. To browse papers by author, here is a list of top authors (KDD-2024). 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 2024, it is to be held in Spain.
This list is created by the Paper Digest Team. Experience the cutting-edge capabilities of Paper Digest, an innovative AI-powered research platform that empowers you to write, review, get answers and more. Try us today and unlock the full potential of our services for free!
TABLE 1: Paper Digest: KDD 2024 Papers & Highlights
| Paper | Author(s) | |
|---|---|---|
| 1 | GEO: Generative Engine Optimization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: With generative engines here to stay, we must ensure the creator economy is not disadvantaged. To address this, we introduce Generative Engine Optimization (GEO), the first novel paradigm to aid content creators in improving their content visibility in generative engine responses through a flexible black-box optimization framework for optimizing and defining visibility metrics. |
Pranjal Aggarwal; Vishvak Murahari; Tanmay Rajpurohit; Ashwin Kalyan; Karthik Narasimhan; Ameet Deshpande; |
| 2 | Approximating Memorization Using Loss Surface Geometry for Dataset Pruning and Summarization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose a novel method that leverages the discrepancy between sharpness-aware minimization and stochastic gradient descent to capture data points atypicality. |
Andrea Agiollo; Young In Kim; Rajiv Khanna; |
| 3 | Resilient K-Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We study the problem of resilient clustering in the metric setting where one is interested in designing algorithms that return high quality solutions that preserve the clustering structure under perturbations of the input points. |
Sara Ahmadian; MohammadHossein Bateni; Hossein Esfandiari; Silvio Lattanzi; Morteza Monemizadeh; Ashkan Norouzi-Fard; |
| 4 | Statistical Models of Top-k Partial Orders Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce and taxonomize approaches for jointly modeling distributions over top-k partial orders and list lengths k, considering two classes of approaches: composite models that view a partial order as a truncation of a total order, and augmented ranking models that model the construction of the list as a sequence of choice decisions, including the decision to stop. |
Amel Awadelkarim; Johan Ugander; |
| 5 | A Learned Generalized Geodesic Distance Function-Based Approach for Node Feature Augmentation on Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce an approach called ‘LGGD’ (Learned Generalized Geodesic Distances). |
Amitoz Azad; Yuan Fang; |
| 6 | Semi-Supervised Learning for Time Series Collected at A Low Sampling Rate Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To reduce data collection and labeling costs while maintaining high classification accuracy, we propose a novel problem setting, called semi-supervised learning with low-sampling-rate time series, in which the majority of time series are collected at a low sampling rate and are unlabeled whereas the minority of time series are collected at a high sampling rate and are labeled. |
Minyoung Bae; Yooju Shin; Youngeun Nam; Young Seop Lee; Jae-Gil Lee; |
| 7 | Understanding Inter-Session Intentions Via Complex Logical Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present the task of logical session complex query answering (LS-CQA), where sessions are treated as hyperedges of items, and we frame the problem of complex intention understanding as an LS-CQA task on an aggregated hypergraph of sessions, items, and attributes. |
Jiaxin Bai; Chen Luo; Zheng Li; Qingyu Yin; Yangqiu Song; |
| 8 | Towards Robust Information Extraction Via Binomial Distribution Guided Counterpart Sequence Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose Binomial distribution guided counterpart sequence (BCS) method, which is a model-agnostic approach. |
Yinhao Bai; Yuhua Zhao; Zhixin Han; Hang Gao; Chao Xue; Mengting Hu; |
| 9 | Meta Clustering of Neural Bandits Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study a new problem, Clustering of Neural Bandits, by extending previous work to the arbitrary reward function, to strike a balance between user heterogeneity and user correlations in the recommender system. To solve this problem, we propose a novel algorithm called M-CNB, which utilizes a meta-learner to represent and rapidly adapt to dynamic clusters, along with an informative Upper Confidence Bound (UCB)-based exploration strategy. |
Yikun Ban; Yunzhe Qi; Tianxin Wei; Lihui Liu; Jingrui He; |
| 10 | Improved Active Covering Via Density-Based Space Transformation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we study active covering, a variant of the active-learning problem that involves labeling (or identifying) all of the examples with a positive label. |
MohammadHossein Bateni; Hossein Esfandiari; Samira HosseinGhorban; Alipasha Montaseri; |
| 11 | Graph Mamba: Towards Learning on Graphs with State Space Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we show that while Transformers, complex message-passing, and PE are sufficient for good performance in practice, neither is necessary. |
Ali Behrouz; Farnoosh Hashemi; |
| 12 | Evading Community Detection Via Counterfactual Neighborhood Search Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we address the challenge of community membership hiding, which involves strategically altering the structural properties of a network graph to prevent one or more nodes from being identified by a given community detection algorithm. |
Andrea Bernini; Fabrizio Silvestri; Gabriele Tolomei; |
| 13 | FaultInsight: Interpreting Hyperscale Data Center Host Faults Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the challenge, this study presents FaultInsight, a highly interpretable deep causal host fault diagnosing framework that offers diagnostic insights from various perspectives to reduce human effort in troubleshooting. |
Tingzhu Bi; Zhang Yang; Yicheng Pan; Yu Zhang; Meng Ma; Xinrui Jiang; Linlin Han; Feng Wang; Xian Liu; Ping Wang; |
| 14 | Learning The Covariance of Treatment Effects Across Many Weak Experiments Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We consider the meta-analysis of many historical experiments to learn the covariance of treatment effects on these outcomes, which can support the construction of such proxies. |
Aur\'{e}lien Bibaut; Winston Chou; Simon Ejdemyr; Nathan Kallus; |
| 15 | Making Temporal Betweenness Computation Faster and Restless Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A new algorithm for temporal betweenness computation is introduced in this paper. |
Filippo Brunelli; Pierluigi Crescenzi; Laurent Viennot; |
| 16 | Where Have You Been? A Study of Privacy Risk for Point-of-Interest Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To better understand and quantify the privacy leakage in mobility data-based ML models, we design a privacy attack suite containing data extraction and membership inference attacks tailored for point-of-interest (POI) recommendation models, one of the most widely used mobility data-based ML models. |
Kunlin Cai; Jinghuai Zhang; Zhiqing Hong; William Shand; Guang Wang; Desheng Zhang; Jianfeng Chi; Yuan Tian; |
| 17 | Popularity-Aware Alignment and Contrast for Mitigating Popularity Bias Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we conduct an empirical analysis of popularity bias and propose Popularity-Aware Alignment and Contrast (PAAC) to address two challenges. |
Miaomiao Cai; Lei Chen; Yifan Wang; Haoyue Bai; Peijie Sun; Le Wu; Min Zhang; Meng Wang; |
| 18 | FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite the emergence of various open source methods and web-enhanced commercial systems such as Bing Chat, two critical problems remain unsolved, i.e., the lack of factuality and clear logic in the generated long-form answers. In this paper, we remedy these issues via a systematic study on answer generation in web-enhanced LFQA. |
Tianchi Cai; Zhiwen Tan; Xierui Song; Tao Sun; Jiyan Jiang; Yunqi Xu; Yinger Zhang; Jinjie Gu; |
| 19 | Tackling Instance-Dependent Label Noise with Class Rebalance and Geometric Regularization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, this extraction process is hindered by severe inter-class imbalance and a bias toward selecting unambiguous intra-class instances, leading to a distorted understanding of noise patterns. To tackle these challenges, our paper introduces a Class Rebalance and Geometric Regularization-based Framework (CRGR). |
Shuzhi Cao; Jianfei Ruan; Bo Dong; Bin Shi; |
| 20 | DiffusionE: Reasoning on Knowledge Graphs Via Diffusion-based Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, they neglect the message interactions between adjacent entities and propagation relations in KG reasoning, leading to semantic inconsistency during the message aggregation phase. To address these issues, we introduce a novel knowledge graph embedding method through a diffusion process, termed DiffusionE. |
Zongsheng Cao; Jing Li; Zigan Wang; Jinliang Li; |
| 21 | Path-based Explanation for Knowledge Graph Completion Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Nonetheless, the methods for generating path-based explanations for KGs have not been well-explored. To address this gap, we propose Power-Link, the first path-based KGC explainer that explores GNN-based models. |
Heng Chang; Jiangnan Ye; Alejo Lopez-Avila; Jinhua Du; Jia Li; |
| 22 | A Hierarchical Context Augmentation Method to Improve Retrieval-Augmented LLMs on Scientific Papers Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: the deduction relationship of abstract and main body, which makes it difficult to grasp the central thought of papers. To tackle this problem, we propose a hierarchical context augmentation method, which helps Retrieval-Augmented LLMs to autoregressively learn the structure knowledge of scientific papers. |
Tian-Yi Che; Xian-Ling Mao; Tian Lan; Heyan Huang; |
| 23 | Harm Mitigation in Recommender Systems Under User Preference Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We establish conditions under which the user profile dynamics have a stationary point, and propose algorithms for finding an optimal recommendation policy at stationarity. |
Jerry Chee; Shankar Kalyanaraman; Sindhu Kiranmai Ernala; Udi Weinsberg; Sarah Dean; Stratis Ioannidis; |
| 24 | Cluster-Wide Task Slowdown Detection in Cloud System Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Though transformer-based methods are one of the most powerful methods to capture these time series normal variation patterns, we empirically find and theoretically explain the flaw of the standard attention mechanism in reconstructing subperiods with low amplitude when dealing with compound periodicity. To tackle these challenges, we propose SORN (i.e., Skimming Off subperiods in descending amplitude order and Reconstructing Non-slowing fluctuation), which consists of a Skimming Attention mechanism to reconstruct the compound periodicity and a Neural Optimal Transport module to distinguish cluster-wide slowdowns from other exceptional fluctuations. |
Feiyi Chen; Yingying Zhang; Lunting Fan; Yuxuan Liang; Guansong Pang; Qingsong Wen; Shuiguang Deng; |
| 25 | Scalable Algorithm for Finding Balanced Subgraphs with Tolerance in Signed Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Traditional models, however, are limited by an assumption of perfect partitioning, which fails to mirror the complexities of real-world data. Addressing this gap, we introduce an innovative generalized balanced subgraph model that incorporates tolerance for imbalance. |
Jingbang Chen; Qiuyang Mang; Hangrui Zhou; Richard Peng; Yu Gao; Chenhao Ma; |
| 26 | Can A Deep Learning Model Be A Sure Bet for Tabular Prediction? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While Gradient Boosting Decision Trees (GBDTs) and existing deep neural networks (DNNs) have been extensively utilized by professional users, they present several challenges for casual users, particularly: (i) the dilemma of model selection due to their different dataset preferences, and (ii) the need for heavy hyperparameter searching, failing which their performances are deemed inadequate. In this paper, we delve into this question: Can we develop a deep learning model that serves as a sure bet solution for a wide range of tabular prediction tasks, while also being user-friendly for casual users? |
Jintai Chen; Jiahuan Yan; Qiyuan Chen; Danny Z. Chen; Jian Wu; Jimeng Sun; |
| 27 | QGRL: Quaternion Graph Representation Learning for Heterogeneous Feature Data Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To inherit the advantages of QRL for unsupervised heterogeneous feature representation learning, we propose a deep QRL model that works in an encoder-decoder manner. |
Junyang Chen; Yuzhu Ji; Rong Zou; Yiqun Zhang; Yiu-ming Cheung; |
| 28 | Large Language Model-driven Meta-structure Discovery in Heterogeneous Information Network Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose ReStruct, a meta-structure search framework that integrates LLM reasoning into the evolutionary procedure. |
Lin Chen; Fengli Xu; Nian Li; Zhenyu Han; Meng Wang; Yong Li; Pan Hui; |
| 29 | Profiling Urban Streets: A Semi-Supervised Prediction Model Based on Street View Imagery and Spatial Topology Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Particularly, street view images have gained popularity for understanding the characteristics of urban areas due to its abundant visual information and inherent correlations with human activities. In this study, we define a street segment represented by multiple street view images as the minimum spatial unit for analysis and predict its functional and socioeconomic indicators, which presents several challenges in modeling spatial distributions of images on a street and the spatial topology (adjacency) of streets. |
Meng Chen; Zechen Li; Weiming Huang; Yongshun Gong; Yilong Yin; |
| 30 | Explicit and Implicit Modeling Via Dual-Path Transformer for Behavior Set-informed Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In BSSR, behavior dependencies become more complex and personalized, and user interest arousal may lack explicit contextual associations. To delve into the dynamics inhered within a behavior set and adaptively tailor recommendation lists upon its variability, we propose a novel solution called Explicit and Implicit modeling via Dual-Path Transformer (EIDP) for BSSR. |
Ming Chen; Weike Pan; Zhong Ming; |
| 31 | Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce a universal calibration methodology for the detection and adaptation of CDS with a trained model. |
Mouxiang Chen; Lefei Shen; Han Fu; Zhuo Li; Jianling Sun; Chenghao Liu; |
| 32 | GraphWiz: An Instruction-Following Language Model for Graph Computational Problems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Large language models (LLMs) have achieved impressive success across various domains, but their capability in understanding and resolving complex graph problems is less explored. To bridge this gap, we introduce GraphInstruct, a novel instruction-tuning dataset aimed at enabling language models to tackle a broad spectrum of graph problems through explicit reasoning paths. |
Nuo Chen; Yuhan Li; Jianheng Tang; Jia Li; |
| 33 | Hate Speech Detection with Generalizable Target-aware Fairness Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To tackle the defects of existing HSD practices, we propose Generalizable target-aware Fairness (GetFair), a new method for fairly classifying each post that contains diverse and even unseen targets during inference. |
Tong Chen; Danny Wang; Xurong Liang; Marten Risius; Gianluca Demartini; Hongzhi Yin; |
| 34 | Maximum-Entropy Regularized Decision Transformer with Reward Relabelling for Dynamic Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In response, we introduce a novel methodology named Max-Entropy enhanced Decision Transformer with Reward Relabeling for Offline RLRS (EDT4Rec). |
Xiaocong Chen; Siyu Wang; Lina Yao; |
| 35 | Shopping Trajectory Representation Learning with Pre-training for E-commerce Customer Understanding and Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes C-STAR, a new framework that learns compact representations from customer shopping journeys, with good versatility to fuel multiple downstream customer-centric tasks. |
Yankai Chen; Quoc-Tuan Truong; Xin Shen; Jin Li; Irwin King; |
| 36 | Conformal Counterfactual Inference Under Hidden Confounding Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Since transductive conformal prediction is notoriously costly, we propose wSCP-DR, a two-stage variant of wTCP-DR, based on split conformal prediction with same marginal coverage guarantees but at a significantly lower computational cost. |
Zonghao Chen; Ruocheng Guo; Jean-Francois Ton; Yang Liu; |
| 37 | DyGKT: Dynamic Graph Learning for Knowledge Tracing Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: The three dynamical characteristics above contain the great potential to revolutionize the existing knowledge tracing methods. Along this line, we propose a Dynamic Graph-based Knowledge Tracing model, namely DyGKT. |
Ke Cheng; Linzhi Peng; Pengyang Wang; Junchen Ye; Leilei Sun; Bowen Du; |
| 38 | Co-Neighbor Encoding Schema: A Light-cost Structure Encoding Method for Dynamic Link Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Besides, unlike the existing memory-based dynamic graph learning method that stores node hidden states, we introduce a hashtable-based memory to compress the adjacency matrix for efficient structure feature construction and updating with vector computation in parallel. |
Ke Cheng; Peng Linzhi; Junchen Ye; Leilei Sun; Bowen Du; |
| 39 | Resurrecting Label Propagation for Graphs with Heterophily and Label Noise Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Following observations, we propose a efficient algorithm, denoted as R2LP. |
Yao Cheng; Caihua Shan; Yifei Shen; Xiang Li; Siqiang Luo; Dongsheng Li; |
| 40 | Retrieval-Augmented Hypergraph for Multimodal Social Media Popularity Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose RAGTrans, an aspect-aware retrieval-augmented multi-modal hypergraph transformer that retrieves pertinent knowledge from a multi-modal memory bank and enhances UGC representations via neighborhood knowledge aggregation on multi-model hypergraphs. |
Zhangtao Cheng; Jienan Zhang; Xovee Xu; Goce Trajcevski; Ting Zhong; Fan Zhou; |
| 41 | Enhancing Contrastive Learning on Graphs with Node Similarity Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Current GCL methods, using data augmentation for positive samples and random selection for negative samples, can be sub-optimal due to limited positive samples and the possibility of false-negative samples. In this study, we propose an enhanced objective addressing these issues. |
Hongliang Chi; Yao Ma; |
| 42 | Iterative Weak Learnability and Multiclass AdaBoost Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an efficient boosting algorithm for multiclass classification, called AdaBoost.Iter, that extends SAMME and AdaBoost. |
In-Koo Cho; Jonathan A. Libgober; Cheng Ding; |
| 43 | Efficient Exploration of The Rashomon Set of Rule-Set Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose, for the first time, efficient methods to explore the Rashomon set of rule-set models with or without exhaustive search. |
Martino Ciaperoni; Han Xiao; Aristides Gionis; |
| 44 | Relevance Meets Diversity: A User-Centric Framework for Knowledge Exploration Through Recommendations Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we put the user at the central stage, and build on the interplay between relevance, diversity, and user behavior. |
Erica Coppolillo; Giuseppe Manco; Aristides Gionis; |
| 45 | Leveraging Pedagogical Theories to Understand Student Learning Process with Graph-based Reasonable Knowledge Tracing Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In response, our research conducts a preliminary analysis of mainstream KT approaches to highlight and explain such unreasonableness. We introduce GRKT, a graph-based reasonable knowledge tracing method to address these issues. |
Jiajun Cui; Hong Qian; Bo Jiang; Wei Zhang; |
| 46 | Fairness in Streaming Submodular Maximization Subject to A Knapsack Constraint Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study the fundamental problem of fair submodular maximization subject to a knapsack constraint and propose the first streaming algorithm for it with provable performance guarantees for both monotone and non-monotone submodular functions. |
Shuang Cui; Kai Han; Shaojie Tang; Feng Li; Jun Luo; |
| 47 | Neural Retrievers Are Biased Towards LLM-Generated Content Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we conduct a quantitative evaluation of IR models in scenarios where both human-written and LLM-generated texts are involved. |
Sunhao Dai; Yuqi Zhou; Liang Pang; Weihao Liu; Xiaolin Hu; Yong Liu; Xiao Zhang; Gang Wang; Jun Xu; |
| 48 | AGS-GNN: Attribute-guided Sampling for Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose AGS-GNN, a novel attribute-guided sampling algorithm for Graph Neural Networks (GNNs). |
Siddhartha Shankar Das; S M Ferdous; Mahantesh M. Halappanavar; Edoardo Serra; Alex Pothen; |
| 49 | Explanatory Model Monitoring to Understand The Effects of Feature Shifts on Performance Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose a novel approach to explain the behavior of a black-box model under feature shifts by attributing an estimated performance change to interpretable input characteristics. |
Thomas Decker; Alexander Koebler; Michael Lebacher; Ingo Thon; Volker Tresp; Florian Buettner; |
| 50 | Unraveling Block Maxima Forecasting Models with Counterfactual Explanation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: As the use of deep neural network models for block maxima forecasting increases, so does the need for explainable AI methods that could unravel the inner workings of such black box models. To fill this need, this paper presents a novel counterfactual explanation framework for block maxima forecasting models. |
Yue Deng; Asadullah Hill Galib; Pang-Ning Tan; Lifeng Luo; |
| 51 | Divide and Denoise: Empowering Simple Models for Robust Semi-Supervised Node Classification Against Label Noise Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we revisit the role of (1) message passing and (2) pseudo labels in the studied problem and try to address two denoising subproblems from the model architecture and algorithm perspective, respectively. |
Kaize Ding; Xiaoxiao Ma; Yixin Liu; Shirui Pan; |
| 52 | Fast Unsupervised Deep Outlier Model Selection with Hypernetworks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we consider a critical-yet-understudied challenge with unsupervised DOD, that is, effective hyperparameter (HP) tuning/model selection. |
Xueying Ding; Yue Zhao; Leman Akoglu; |
| 53 | Enhancing On-Device LLM Inference with Historical Cloud-Based LLM Interactions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We thus propose to collect the user’s historical interactions with the cloud-based LLM and build an external datastore on the mobile device for enhancement using nearest neighbors search. |
Yucheng Ding; Chaoyue Niu; Fan Wu; Shaojie Tang; Chengfei Lyu; Guihai Chen; |
| 54 | Unsupervised Alignment of Hypergraphs with Different Scales Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose and tackle the problem of unsupervised hypergraph alignment. |
Manh Tuan Do; Kijung Shin; |
| 55 | IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a principled framework named IDEA to achieve flexible and certified unlearning for GNNs. |
Yushun Dong; Binchi Zhang; Zhenyu Lei; Na Zou; Jundong Li; |
| 56 | Heterogeneity-Informed Meta-Parameter Learning for Spatiotemporal Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: While significant progress has been made in this area, fully capturing and leveraging spatiotemporal heterogeneity remains a fundamental challenge. Therefore, we propose a novel Heterogeneity-Informed Meta-Parameter Learning scheme. |
Zheng Dong; Renhe Jiang; Haotian Gao; Hangchen Liu; Jinliang Deng; Qingsong Wen; Xuan Song; |
| 57 | Estimated Judge Reliabilities for Weighted Bradley-Terry-Luce Are Not Reliable Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Several methods have been proposed to assign weights to judges based on their responses relative to everyone else, the goal being to reduce exposure to poor performers, hopefully upgrading the quality of the data.Our research focuses on two natural extensions to the Bradley-Terry-Luce formulation of scaling that jointly optimize for both scale value and judge weights. |
Andrew F. Dreher; Etienne Vouga; Donald S. Fussell; |
| 58 | Representation Learning of Temporal Graphs with Structural Roles Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, underestimating the inherent global structural role information in many real-world temporal graphs inevitably leads to sub-optimal graph representations. To overcome this shortcoming, we propose a novel Role-based Temporal Graph Convolution Network (RTGCN) that fully leverages the global structural role information in temporal graphs. |
Huaming Du; Long Shi; Xingyan Chen; Yu Zhao; Hegui Zhang; Carl Yang; Fuzhen Zhuang; Gang Kou; |
| 59 | DisCo: Towards Harmonious Disentanglement and Collaboration Between Tabular and Semantic Space for Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose DisCo to Disentangle the unique patterns from the two representation spaces and Collaborate the two spaces for recommendation enhancement, where both the specificity and the consistency of the two spaces are captured. |
Kounianhua Du; Jizheng Chen; Jianghao Lin; Yunjia Xi; Hangyu Wang; Xinyi Dai; Bo Chen; Ruiming Tang; Weinan Zhang; |
| 60 | Disentangled Multi-interest Representation Learning for Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a generic multi-interest method for sequential recommendation, achieving disentangled representation learning of diverse interests technically and theoretically. |
Yingpeng Du; Ziyan Wang; Zhu Sun; Yining Ma; Hongzhi Liu; Jie Zhang; |
| 61 | Reserving-Masking-Reconstruction Model for Self-Supervised Heterogeneous Graph Representation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, this paper proposes a Reserving-Masking-Reconstruction (RMR) model that can fully consider heterogeneous information without relying on the metapaths. |
Haoran Duan; Cheng Xie; Linyu Li; |
| 62 | Pre-Training Identification of Graph Winning Tickets in Adaptive Spatial-Temporal Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a novel method to significantly enhance the computational efficiency of Adaptive Spatial-Temporal Graph Neural Networks (ASTGNNs) by introducing the concept of the Graph Winning Ticket (GWT), derived from the Lottery Ticket Hypothesis (LTH). |
Wenying Duan; Tianxiang Fang; Hong Rao; Xiaoxi He; |
| 63 | Auctions with LLM Summaries Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel factorized framework in which an auction module and an LLM module work together via a prediction model to provide welfare maximizing summary outputs in an incentive compatible manner. |
Avinava Dubey; Zhe Feng; Rahul Kidambi; Aranyak Mehta; Di Wang; |
| 64 | CAT: Interpretable Concept-based Taylor Additive Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, these methods require domain experts to extensively label concepts with relevant names and their ground-truth values. In response, we propose CAT, a novel interpretable Concept-bAsed Taylor additive model to simplify this process. |
Viet Duong; Qiong Wu; Zhengyi Zhou; Hongjue Zhao; Chenxiang Luo; Eric Zavesky; Huaxiu Yao; Huajie Shao; |
| 65 | Label Shift Correction Via Bidirectional Marginal Distribution Matching Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To correct the label shift, existing methods estimate the true label distribution by prediction of target data from a source classifier, which results in high variance, especially with large label shift. In this paper, we tackle this problem by proposing a novel approach termed as Label Shift Correction via Bidirectional Marginal Distribution Matching (BMDM). |
Ruidong Fan; Xiao Ouyang; Hong Tao; Chenping Hou; |
| 66 | GAugLLM: Improving Graph Contrastive Learning for Text-Attributed Graphs with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To bridge the gap, we introduce GAugLLM, a novel framework for augmenting TAGs. |
Yi Fang; Dongzhe Fan; Daochen Zha; Qiaoyu Tan; |
| 67 | ROTAN: A Rotation-based Temporal Attention Network for Time-Specific Next POI Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a brand new Time2Rotation technique to capture the temporal information. |
Shanshan Feng; Feiyu Meng; Lisi Chen; Shuo Shang; Yew Soon Ong; |
| 68 | Influence Maximization Via Graph Neural Bandits Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We consider a ubiquitous scenario in the study of Influence Maximization (IM), in which there is limited knowledge about the topology of the diffusion network. |
Yuting Feng; Vincent Y.F. Tan; Bogdan Cautis; |
| 69 | SensitiveHUE: Multivariate Time Series Anomaly Detection By Enhancing The Sensitivity to Normal Patterns Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we emphasize the necessity of sensitivity to normal patterns, which could improve the discrimination between normal and abnormal points remarkably. |
Yuye Feng; Wei Zhang; Yao Fu; Weihao Jiang; Jiang Zhu; Wenqi Ren; |
| 70 | Communication-efficient Multi-service Mobile Traffic Prediction By Leveraging Cross-service Correlations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, such isolated prediction methods necessitate the uploading of historical traffic data from all regions to forecast city-wide traffic, resulting in consuming substantial bandwidth resources and risking prediction failure in the event of data loss in specific regions. To address these challenges, we propose a novel Cross-service Attention-based Spatial-Temporal Graph Convolutional Network (CsASTGCN) for precise and communication-efficient multi-service mobile traffic prediction. |
Zhiying Feng; Qiong Wu; Xu Chen; |
| 71 | AutoXPCR: Automated Multi-Objective Model Selection for Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose AutoXPCR – a novel method that produces DNNs for forecasting under consideration of multiple objectives in an automated and explainable fashion. |
Raphael Fischer; Amal Saadallah; |
| 72 | DIET: Customized Slimming for Incompatible Networks in Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The former may disrupt other processes on the edge to acquire computational resources, while the latter consumes network bandwidth, leading to a decrease in user satisfaction. In response to these challenges, we propose a customizeD slImming framework for incompatiblE neTworks(DIET). |
Kairui Fu; Shengyu Zhang; Zheqi Lv; Jingyuan Chen; Jiwei Li; |
| 73 | Federated Graph Learning with Structure Proxy Alignment Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Moreover, FGL also encounters a unique challenge for the node classification task: the nodes from a minority class in a client are more likely to have biased neighboring information, which prevents FGL from learning expressive node embeddings with Graph Neural Networks (GNNs). To grapple with the challenge, we propose FedSpray, a novel FGL framework that learns local class-wise structure proxies in the latent space and aligns them to obtain global structure proxies in the server. |
Xingbo Fu; Zihan Chen; Binchi Zhang; Chen Chen; Jundong Li; |
| 74 | Policy-Based Bayesian Active Causal Discovery with Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we propose a novel method called Reinforcement Learning-based Causal Bayesian Experimental Design (RL-CBED) to reduce the risk of local optimality and accelerate intervention selection inference. |
Heyang Gao; Zexu Sun; Hao Yang; Xu Chen; |
| 75 | Graph Condensation for Open-World Graph Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Consequently, due to the limited generalization capacity of condensed graphs, applications that employ GC for efficient GNN training end up with sub-optimal GNNs when confronted with evolving graph structures and distributions in dynamic real-world situations. To overcome this issue, we propose open-world graph condensation (OpenGC), a robust GC framework that integrates structure-aware distribution shift to simulate evolving graph patterns and exploit the temporal environments for invariance condensation. |
Xinyi Gao; Tong Chen; Wentao Zhang; Yayong Li; Xiangguo Sun; Hongzhi Yin; |
| 76 | Online Preference Weight Estimation Algorithm with Vanishing Regret for Car-Hailing in Road Network Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, a set of preference weight estimation models is employed to capture the users’ preferences over paths in car-hailing with their historical choices. |
Yucen Gao; Zhehao Zhu; Mingqian Ma; Fei Gao; Hui Gao; Yangguang Shi; Xiaofeng Gao; |
| 77 | PATE: Proximity-Aware Time Series Anomaly Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce Proximity-Aware Time series anomaly Evaluation (PATE), a novel evaluation metric that incorporates the temporal relationship between prediction and anomaly intervals. |
Ramin Ghorbani; Marcel J.T. Reinders; David M.J. Tax; |
| 78 | Hierarchical Neural Constructive Solver for Real-world TSP Scenarios Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce realistic Traveling Salesman Problem (TSP) scenarios relevant to industrial settings and derive the following insights: (1) The optimal next node (or city) to visit often lies within proximity to the current node, suggesting the potential benefits of biasing choices based on current locations. |
Yong Liang Goh; Zhiguang Cao; Yining Ma; Yanfei Dong; Mohammed Haroon Dupty; Wee Sun Lee; |
| 79 | A Population-to-individual Tuning Framework for Adapting Pretrained LM to On-device User Intent Prediction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Leveraging pre-trained language models (PLMs) offers a promising avenue, yet adapting PLMs to on-device user intent prediction presents significant challenges. To address these challenges, we propose PITuning, a Population-to-Individual Tuning framework. |
Jiahui Gong; Jingtao Ding; Fanjin Meng; Guilong Chen; Hong Chen; Shen Zhao; Haisheng Lu; Yong Li; |
| 80 | An Energy-centric Framework for Category-free Out-of-distribution Node Detection in Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, the nodes in the graph might not be pre-labeled with specific categories, rendering entropy-based OOD detectors inapplicable in such category-free situations. To tackle this issue, we propose an energy-centric density estimation framework for OOD node detection, referred to as EnergyDef. |
Zheng Gong; Ying Sun; |
| 81 | Topology-Driven Multi-View Clustering Via Tensorial Refined Sigmoid Rank Minimization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Additionally, mainstream techniques are constrained by equally shrinking all singular values to recover a low-rank tensor, limiting their capacity to distinguish significant variations among different singular values. In this investigation, we present an innovative TMVC framework termed toPology-driven multi-view clustering viA refined teNsorial sigmoiD rAnk minimization (PANDA ). |
Zhibin Gu; Zhendong Li; Songhe Feng; |
| 82 | Investigating Out-of-Distribution Generalization of GNNs: An Architecture Perspective Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we provide the first comprehensive investigation of OOD generalization on graphs from an architecture perspective, by examining the common building blocks of modern GNNs. |
Kai Guo; Hongzhi Wen; Wei Jin; Yaming Guo; Jiliang Tang; Yi Chang; |
| 83 | Consistency and Discrepancy-Based Contrastive Tripartite Graph Learning for Recommendations Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Despite their effectiveness, these systems exacerbate the long-standing cold-start problem in traditional recommender systems, because any number of user groups or item bundles can be formed among users or items. To address this issue, we introduce a Consistency and Discrepancy-based graph contrastive learning method for tripartite graph-based Recommendation (CDR). |
Linxin Guo; Yaochen Zhu; Min Gao; Yinghui Tao; Junliang Yu; Chen Chen; |
| 84 | Ranking with Slot Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we formalize the slot-constrained ranking problem as producing a ranking that maximizes the number of filled slots if candidates are evaluated by a human decision maker for slot eligibility in the order of the ranking. |
Wentao Guo; Andrew Wang; Bradon Thymes; Thorsten Joachims; |
| 85 | HiFGL: A Hierarchical Framework for Cross-silo Cross-device Federated Graph Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, in this paper, we propose a Hierarchical Federated Graph Learning (HiFGL) framework for cross-silo cross-device FGL. |
Zhuoning Guo; Duanyi Yao; Qiang Yang; Hao Liu; |
| 86 | Binder: Hierarchical Concept Representation Through Order Embedding of Binary Vectors Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose Binder, a novel approach for order-based representation. |
Croix Gyurek; Niloy Talukder; Mohammad Al Hasan; |
| 87 | AnyLoss: Transforming Classification Metrics Into Loss Functions Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose a general-purpose approach that transforms any confusion matrix-based metric into a loss function, AnyLoss, that is available in optimization processes. |
Doheon Han; Nuno Moniz; Nitesh V. Chawla; |
| 88 | Adapting Job Recommendations to User Preference Drift with Behavioral-Semantic Fusion Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: The inherent frequency of preference drift poses a challenge to promptly and precisely capture user preferences. To address this issue, we propose a novel session-based framework, BISTRO, to timely model user preference through fusion learning of semantic and behavioral information. |
Xiao Han; Chen Zhu; Xiao Hu; Chuan Qin; Xiangyu Zhao; Hengshu Zhu; |
| 89 | Expander Hierarchies for Normalized Cuts on Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we introduce the first practically efficient algorithm for computing expander decompositions and their hierarchies and demonstrate its effectiveness and utility by incorporating it as the core component in a novel solver for the normalized cut graph clustering objective. |
Kathrin Hanauer; Monika Henzinger; Robin M\{u}nk; Harald R\{a}cke; Maximilian V\{o}tsch; |
| 90 | A Unified Core Structure in Multiplex Networks: From Finding The Densest Subgraph to Modeling User Engagement Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce Score, a novel and unifying family of dense structures in multiplex networks that uses a function S(.) |
Farnoosh Hashemi; Ali Behrouz; |
| 91 | An Efficient Local Search Algorithm for Large GD Advertising Inventory Allocation with Multilinear Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Existing methods which rely on the convex properties are not suitable for processing this problem, while mathematical programming or constraint-based heuristic solvers are unable to produce high-quality solutions within the time limit. Therefore, we propose a local search framework to address this challenge. |
Xiang He; Wuyang Mao; Zhenghang Xu; Yuanzhe Gu; Yundu Huang; Zhonglin Zu; Liang Wang; Mengyu Zhao; Mengchuan Zou; |
| 92 | Model-Agnostic Random Weighting for Out-of-Distribution Generalization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In response to the problem, we propose a simple model-agnostic method tailored for a practical OOD scenario in this paper. |
Yue He; Pengfei Tian; Renzhe Xu; Xinwei Shen; Xingxuan Zhang; Peng Cui; |
| 93 | Double Correction Framework for Denoising Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: (1) High training losses can result from model optimization instability or hard samples, not just noisy samples. (2) Completely dropping of noisy samples will aggravate the data sparsity, which lacks full data exploitation.To tackle the above limitations, we propose a Double Correction Framework for Denoising Recommendation (DCF), which contains two correction components from views of more precise sample dropping and avoiding more sparse data. |
Zhuangzhuang He; Yifan Wang; Yonghui Yang; Peijie Sun; Le Wu; Haoyue Bai; Jinqi Gong; Richang Hong; Min Zhang; |
| 94 | Budgeted Multi-Armed Bandits with Asymmetric Confidence Intervals Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To overcome them, we propose a new upper confidence bound (UCB) sampling policy, \o{}mega-UCB, that uses asymmetric confidence intervals. |
Marco Heyden; Vadim Arzamasov; Edouard Fouch\'{e}; Klemens B\{o}hm; |
| 95 | RoutePlacer: An End-to-End Routability-Aware Placer with Graph Neural Network Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This method hinders jointly optimizing the routability aspect during placement. To address this problem, this work introduces RoutePlacer, an end-to-end routability-aware placement method. |
Yunbo Hou; Haoran Ye; Yingxue Zhang; Siyuan Xu; Guojie Song; |
| 96 | Is Aggregation The Only Choice? Federated Learning Via Layer-wise Model Recombination Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Aggregating local models usually results in a low-generalized global model, which performs worse on most of the clients. To address the above issue, inspired by the observation from a geometric perspective that a well-generalized solution is located in a flat area rather than a sharp area, we propose a novel and heuristic FL paradigm named FedMR (Federated Model Recombination). |
Ming Hu; Zhihao Yue; Xiaofei Xie; Cheng Chen; Yihao Huang; Xian Wei; Xiang Lian; Yang Liu; Mingsong Chen; |
| 97 | Privacy-Preserved Neural Graph Databases Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose a privacy-preserved neural graph database (P-NGDB) framework to alleviate the risks of privacy leakage in NGDBs. |
Qi Hu; Haoran Li; Jiaxin Bai; Zihao Wang; Yangqiu Song; |
| 98 | Prompt Perturbation in Retrieval-Augmented Generation Based Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we find that the insertion of even a short prefix to the prompt leads to the generation of outputs far away from factually correct answers. |
Zhibo Hu; Chen Wang; Yanfeng Shu; Hye-Young Paik; Liming Zhu; |
| 99 | Can Modifying Data Address Graph Domain Adaptation? Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: By revisiting the theoretical generalization bound for UGDA, we identify two data-centric principles for UGDA: alignment principle and rescaling principle. Guided by these principles, we propose GraphAlign, a novel UGDA method that generates a small yet transferable graph. |
Renhong Huang; Jiarong Xu; Xin Jiang; Ruichuan An; Yang Yang; |
| 100 | EntropyStop: Unsupervised Deep Outlier Detection with Loss Entropy Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To circumvent the need for labels, we propose a zero-label entropy metric named Loss Entropy for loss distribution, enabling us to infer optimal stopping points for training without labels. |
Yihong Huang; Yuang Zhang; Liping Wang; Fan Zhang; Xuemin Lin; |
| 101 | RC-Mixup: A Data Augmentation Strategy Against Noisy Data for Regression Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We thus propose our data augmentation strategy RC-Mixup, which tightly integrates C-Mixup with multi-round robust training methods for a synergistic effect. |
Seong-Hyeon Hwang; Minsu Kim; Steven Euijong Whang; |
| 102 | Learn Together Stop Apart: An Inclusive Approach to Ensemble Pruning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose two methods: Direct Supervised Partition (DSP) and Indirect Supervised Partition (ISP). |
Bulat Ibragimov; Gleb Gusev; |
| 103 | Uplift Modelling Via Gradient Boosting Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Uplift modeling is a challenging task that necessitates a known target for the precise computation of the training gradient. The prevailing two-model strategies, which separately model treatment and control outcomes, are encumbered with limitations as they fail to directly tackle the uplift problem.This paper presents an innovative approach to uplift modeling that employs Gradient Boosting. |
Bulat Ibragimov; Anton Vakhrushev; |
| 104 | Efficient Discovery of Time Series Motifs Under Both Length Differences and Warping Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a novel approach that allows us to find motifs under both length differences and warping. |
Makoto Imamura; Takaaki Nakamura; |
| 105 | Promoting Fairness and Priority in Selecting K-Winners Using IRV Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate the problem of finding winner(s) given a large number of users’ (voters’) preferences casted as ballots, one from each of the m users, where each ballot is a ranked order of preference of up to l out of n items (candidates). |
Md Mouinul Islam; Soroush Vahidi; Baruch Schieber; Senjuti Basu Roy; |
| 106 | FreQuant: A Reinforcement-Learning Based Adaptive Portfolio Optimization with Multi-frequency Decomposition Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose FreQuant (Adaptive Portfolio Optimization via Multi-Frequency Quantitative Analysis), an effective deep RL framework for portfolio optimization that fully operates in the frequency domain, tackling the limitations of time domain-focused models. |
Jihyeong Jeon; Jiwon Park; Chanhee Park; U Kang; |
| 107 | On (Normalised) Discounted Cumulative Gain As An Off-Policy Evaluation Metric for Top-n Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Several offline evaluation metrics have been adopted in the literature, inspired by ranking metrics prevalent in the field of Information Retrieval. (Normalised) Discounted Cumulative Gain (nDCG) is one such metric that has seen widespread adoption in empirical studies, and higher (n)DCG values have been used to present new methods as the state-of-the-art in top-n recommendation for many years.Our work takes a critical look at this approach, and investigates when we can expect such metrics to approximate the gold standard outcome of an online experiment. |
Olivier Jeunen; Ivan Potapov; Aleksei Ustimenko; |
| 108 | Addressing Prediction Delays in Time Series Forecasting: A Continuous GRU Approach with Derivative Regularization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper proposes a new perspective on traditional time series forecasting tasks and introduces a new solution to mitigate the prediction delay. |
Sheo Yon Jhin; Seojin Kim; Noseong Park; |
| 109 | Tensorized Unaligned Multi-view Clustering with Multi-scale Representation Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address these issues, we proposed a novel UMC framework termed Tensorized Unaligned Multi-view Clustering with Multi-scale Representation Learning (TUMCR). |
Jintian Ji; Songhe Feng; Yidong Li; |
| 110 | MemMap: An Adaptive and Latent Memory Structure for Dynamic Graph Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Among these studies, a critical issue is how to update the representations of nodes when new temporal events are observed. In this paper, we provide a novel memory structure – Memory Map (MemMap) for this problem. |
Shuo Ji; Mingzhe Liu; Leilei Sun; Chuanren Liu; Tongyu Zhu; |
| 111 | FairMatch: Promoting Partial Label Learning By Unlabeled Samples Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel method FairMatch, which adopts a learning state aware self-adaptive threshold for selecting the same number of high-confidence samples on each class, and uses augmentation consistency to incorporate the unlabeled samples to promote PLL. |
Jiahao Jiang; Yuheng Jia; Hui Liu; Junhui Hou; |
| 112 | Mutual Distillation Extracting Spatial-temporal Knowledge for Lightweight Multi-channel Sleep Stage Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To solve the problem, we propose a general knowledge distillation framework for multi-channel sleep stage classification called spatial-temporal mutual distillation. |
Ziyu Jia; Haichao Wang; Yucheng Liu; Tianzi Jiang; |
| 113 | Automatic Multi-Task Learning Framework with Neural Architecture Search in Recommendations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Additionally, homogeneous expert architectures in such models further limit their performance. To address these issues, in this paper, we propose an innovative automatic MTL framework, AutoMTL, leveraging neural architecture search (NAS) to design optimal expert architectures and sharing modes. |
Shen Jiang; Guanghui Zhu; Yue Wang; Chunfeng Yuan; Yihua Huang; |
| 114 | Killing Two Birds with One Stone: Cross-modal Reinforced Prompting for Graph and Language Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: First, the language corpus of downstream tasks differs significantly from graph data, making it hard to bridge the knowledge gap between modalities. Second, not all knowledge demonstrates immediate benefits for downstream tasks, potentially introducing disruptive noise to context-sensitive models like LLMs. To tackle these challenges, we propose a novel plug-and-play framework for incorporating a lightweight cross-domain prompting method into both language and graph learning tasks. |
Wenyuan Jiang; Wenwei Wu; Le Zhang; Zixuan Yuan; Jian Xiang; Jingbo Zhou; Hui Xiong; |
| 115 | RCTD: Reputation-Constrained Truth Discovery in Sybil Attack Crowdsourcing Environment Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Specifically, we propose a method called RCTD (Reputation-Constrained Truth Discovery), which introduces a similarity metric between the rankings of workers’ weights and the refined approval rates. |
Xing Jin; Zhihai Gong; Jiuchuan Jiang; Chao Wang; Jian Zhang; Zhen Wang; |
| 116 | Sketch-Based Replay Projection for Continual Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Replay-based continual learning methods mitigate forgetting and improve performance by reintroducing data belonging to old tasks, however a replay method’s performance may deteriorate when the reintroduced data does not effectively represent all experienced data. To address this concern, we propose the Sketch-based Replay Projection (SRP) method to capture and retain the original data stream’s distribution within stored memory. |
Jack Julian; Yun Sing Koh; Albert Bifet; |
| 117 | Bivariate Decision Trees: Smaller, Interpretable, More Accurate Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We advocate for a model that strikes a useful middle ground: bivariate decision trees, which use two features in each node. |
Rasul Kairgeldin; Miguel \'{A}. Carreira-Perpi\~{n}\'{a}n; |
| 118 | Masked LoGoNet: Fast and Accurate 3D Image Analysis for Medical Domain Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Additionally, upon deployment, these methods are usually used to process a large volume of data on a daily basis, imposing a high maintenance cost on medical facilities. In this paper, we introduce a new neural network architecture, termed LoGoNet, with a tailored self-supervised learning (SSL) method to mitigate such challenges. |
Amin Karimi Monsefi; Payam Karisani; Mengxi Zhou; Stacey Choi; Nathan Doble; Heng Ji; Srinivasan Parthasarathy; Rajiv Ramnath; |
| 119 | Gandalf: Learning Label-label Correlations in Extreme Multi-label Classification Via Label Features Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose Gandalf, a novel approach which makes use of a label co-occurrence graph to leverage label features as additional data points to supplement the training distribution. |
Siddhant Kharbanda; Devaansh Gupta; Erik Schultheis; Atmadeep Banerjee; Cho-Jui Hsieh; Rohit Babbar; |
| 120 | CAFO: Feature-Centric Explanation on Time Series Classification Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This limitation underscores the pressing need for a feature-centric approach, a vital yet often overlooked perspective that complements time-centric analysis. To bridge this gap, our study introduces a novel feature-centric explanation and evaluation framework for MTS, named CAFO (Channel Attention and Feature Orthgonalization). |
Jaeho Kim; Seok-Ju Hahn; Yoontae Hwang; Junghye Lee; Seulki Lee; |
| 121 | Fast and Accurate Domain Adaptation for Irregular Tensor Decomposition Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose Meta-P2, a fast and accurate domain adaptation method for irregular tensor decomposition. |
Junghun Kim; Ka Hyun Park; Jun-Gi Jang; U Kang; |
| 122 | Large Language Models Meet Collaborative Filtering: An Efficient All-round LLM-based Recommender System Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose an efficient All-round LLM-based Recommender system, called A-LLMRec, that excels not only in the cold scenario but also in the warm scenario. |
Sein Kim; Hongseok Kang; Seungyoon Choi; Donghyun Kim; Minchul Yang; Chanyoung Park; |
| 123 | OntoType: Ontology-Guided and Pre-Trained Language Model Assisted Fine-Grained Entity Typing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we vision that an ontology provides a semantics-rich, hierarchical structure, which will help select the best results generated by multiple PLM models and head words. |
Tanay Komarlu; Minhao Jiang; Xuan Wang; Jiawei Han; |
| 124 | LeMon: Automating Portrait Generation for Zero-Shot Story Visualization with Multi-Character Interactions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address the challenge of automated multi-character ZSV, aiming to create distinctive yet compatible character portraits for high-quality story visualization without the need of manual human interventions. |
Ziyi Kou; Shichao Pei; Xiangliang Zhang; |
| 125 | Attacking Graph Neural Networks with Bit Flips: Weisfeiler and Leman Go Indifferent Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Hence, we discuss the Injectivity Bit Flip Attack, the first bit flip attack designed specifically for graph neural networks. |
Lorenz Kummer; Samir Moustafa; Sebastian Schrittwieser; Wilfried Gansterer; Nils Kriege; |
| 126 | Max-Min Diversification with Asymmetric Distances Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we initiate the study of the Asymmetric Max-Min Diversification (AMMD) problem. |
Iiro Kumpulainen; Florian Adriaens; Nikolaj Tatti; |
| 127 | Compact Decomposition of Irregular Tensors for Data Compression: From Sparse to Dense to High-Order Tensors Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose accurate and compact decomposition methods for lossy compression of irregular tensors. |
Taehyung Kwon; Jihoon Ko; Jinhong Jung; Jun-Gi Jang; Kijung Shin; |
| 128 | Efficient Topology-aware Data Augmentation for High-Degree Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Motivated by the above limitations, we propose TADA, an efficient and effective front-mounted data augmentation framework for GNNs on HDGs. |
Yurui Lai; Xiaoyang Lin; Renchi Yang; Hongtao Wang; |
| 129 | ReCTSi: Resource-efficient Correlated Time Series Imputation Via Decoupled Pattern Learning and Completeness-aware Attentions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents ReCTSi (Resource-efficient CTS imputation), a method that adopts a new architecture for decoupled pattern learning in two phases: (1) the Persistent Pattern Extraction phase utilizes a multi-view learnable codebook mechanism to identify and archive persistent patterns common across different time series, enabling rapid pattern retrieval during inference. |
Zhichen Lai; Dalin Zhang; Huan Li; Dongxiang Zhang; Hua Lu; Christian S. Jensen; |
| 130 | ShapeFormer: Shapelet Transformer for Multivariate Time Series Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This leads to poor performance in the case of imbalanced datasets or datasets with similar overall patterns but differing in minor class-specific details. In this paper, we propose a novel Shapelet Transformer (ShapeFormer), which comprises class-specific and generic transformer modules to capture both of these features. |
Xuan-May Le; Ling Luo; Uwe Aickelin; Minh-Tuan Tran; |
| 131 | Continual Collaborative Distillation for Recommender System Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we delve into a systematic approach to operating the teacher-student KD in a non-stationary data stream. |
Gyuseok Lee; SeongKu Kang; Wonbin Kweon; Hwanjo Yu; |
| 132 | SLADE: Detecting Dynamic Anomalies in Edge Streams Without Labels Via Self-Supervised Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: While they typically assume static input graphs, most real-world graphs grow over time, naturally represented as edge streams. In this context, we aim to achieve three goals: (a) instantly detecting anomalies as they occur, (b) adapting to dynamically changing states, and (c) handling the scarcity of dynamic anomaly labels.In this paper, we propose SLADE (Self-supervised Learning for Anomaly Detection in Edge Streams) for rapid detection of dynamic anomalies in edge streams, without relying on labels. |
Jongha Lee; Sunwoo Kim; Kijung Shin; |
| 133 | Layer-Wise Adaptive Gradient Norm Penalizing Method for Efficient and Accurate Deep Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A few variants of SAM have been proposed to tackle such an issue, but they commonly do not alleviate the cost noticeably. In this paper, we propose a lightweight layer-wise gradient norm penalizing method that tackles the expensive computational cost of SAM while maintaining its superior generalization performance. |
Sunwoo Lee; |
| 134 | RecExplainer: Aligning Large Language Models for Explaining Recommendation Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To facilitate an effective alignment, we introduce three methods: behavior alignment, intention alignment, and hybrid alignment. |
Yuxuan Lei; Jianxun Lian; Jing Yao; Xu Huang; Defu Lian; Xing Xie; |
| 135 | Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Naively computing either of them requires repeatedly training on data pooled from various task combinations, which is computationally intensive. We present a new algorithm Grad-TAG that can estimate task affinities without this repeated training. |
Dongyue Li; Aneesh Sharma; Hongyang R. Zhang; |
| 136 | Dynamic Neural Dowker Network: Approximating Persistent Homology in Dynamic Directed Graphs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper introduces the Dynamic Neural Dowker Network (DNDN), a novel framework specifically designed to approximate the results of dynamic Dowker filtration, aiming to capture the high-order topological features of dynamic directed graphs. |
Hao Li; Hao Jiang; Fan Jiajun; Dongsheng Ye; Liang Du; |
| 137 | Truthful Bandit Mechanisms for Repeated Two-stage Ad Auctions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we investigate the online learning process of the first-stage subset selection policy, while ensuring game-theoretic properties in repeated two-stage ad auctions. |
Haoming Li; Yumou Liu; Zhenzhe Zheng; Zhilin Zhang; Jian Xu; Fan Wu; |
| 138 | Debiased Recommendation with Noisy Feedback Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we study intersectional threats to the unbiased learning of the prediction model from data MNAR and OME in the collected data. |
Haoxuan Li; Chunyuan Zheng; Wenjie Wang; Hao Wang; Fuli Feng; Xiao-Hua Zhou; |
| 139 | Physics-informed Neural ODE for Post-disaster Mobility Recovery Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Existing models for post-disaster mobility recovery predominantly employ basic mathematical methods, which are strongly based on simplifying assumptions, and their limited parameters restrict their capacity to fully capture the mobility recovery patterns. In response to this gap, we introduce the Coupled Dynamic Graph ODE Network (CDGON) to model the intricate dynamics of post-disaster mobility recovery. |
Jiahao Li; Huandong Wang; Xinlei Chen; |
| 140 | Label Learning Method Based on Tensor Projection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, such methods have high requirements on parameters, and in some cases it may not be possible to obtain bipartite graphs with clear connected components. To end this, we propose a label learning method based on tensor projection (LLMTP). |
Jing Li; Quanxue Gao; Qianqian Wang; Cheng Deng; Deyan Xie; |
| 141 | Causal Subgraph Learning for Generalizable Inductive Relation Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Herein, we introduce a novel front-door adjustment-based approach designed to learn the causal relationship between subgraphs and their ground-truth labels, specifically for inductive relation prediction. |
Mei Li; Xiaoguang Liu; Hua Ji; Shuangjia Zheng; |
| 142 | Privileged Knowledge State Distillation for Reinforcement Learning-based Educational Path Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce the privileged feature distillation technique and propose the P rivileged K nowledge S tate D istillation (PKSD ) framework, allowing the RL agent to leverage the actual” knowledge state as privileged information in the state encoding to help tailor recommendations to meet individual needs. |
Qingyao Li; Wei Xia; Li’ang Yin; Jiarui Jin; Yong Yu; |
| 143 | SimDiff: Simple Denoising Probabilistic Latent Diffusion Model for Data Augmentation on Multi-modal Knowledge Graph Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we address the challenges of data augmentation in Multi-Modal Knowledge Graphs (MMKGs), a relatively under-explored area. |
Ran Li; Shimin Di; Lei Chen; Xiaofang Zhou; |
| 144 | ITPNet: Towards Instantaneous Trajectory Prediction for Autonomous Driving Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we put forward a general and plug-and-play instantaneous trajectory prediction approach, called ITPNet. Specifically, we propose a backward forecasting mechanism to reversely predict the latent feature representations of unobserved historical trajectories of the agent based on its two observed locations and then leverage them as complementary information for future trajectory prediction. |
Rongqing Li; Changsheng Li; Yuhang Li; Hanjie Li; Yi Chen; Ye Yuan; Guoren Wang; |
| 145 | Predicting Long-term Dynamics of Complex Networks Via Identifying Skeleton in Hyperbolic Space Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This is because they overlook the fact that long-term dynamics in complex network are predominantly governed by their inherent low-dimensional manifolds, i.e., skeletons. Therefore, we propose the Dynamics-Invariant Skeleton Neural Network (DiskNet), which identifies skeletons of complex networks based on the renormalization group structure in hyperbolic space to preserve both topological and dynamics properties. |
Ruikun Li; Huandong Wang; Jinghua Piao; Qingmin Liao; Yong Li; |
| 146 | Self-Distilled Disentangled Learning for Counterfactual Prediction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: An appealing method for achieving the independent separation of these factors is mutual information minimization, a task that presents challenges in numerous machine learning scenarios, especially within high-dimensional spaces. To circumvent this challenge, we propose the Self-Distilled Disentanglement framework, referred to as SD2. |
Xinshu Li; Mingming Gong; Lina Yao; |
| 147 | InLN: Knowledge-aware Incremental Leveling Network for Dynamic Advertising Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This results in an uneven distribution of temporal and semantic information, causing existing GNNs to fail in this scenario. In this work, we quantitatively define the above phenomenon as temporal unevenness and introduce the Incremental Leveling Network (InLN) with three novel techniques: the periodic-focusing window for node-level dynamic modeling, the biased temporal walk for subgraph-level dynamic modeling and the incremental leveling mechanism for KG updating. |
Xujia Li; Jingshu Peng; Lei Chen; |
| 148 | Bi-Objective Contract Allocation for Guaranteed Delivery Advertising Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For example, contracts are formulated offline without concerning practical situations in the online serving stage. Therefore, we address in this paper a bi-objective contract allocation for GD advertising, which maximizes the impressions, i.e., Ad resource assignments, allocated for the new incoming advertising orders, and at the same time, controls the balance in the inventories. |
Yan Li; Yundu Huang; Wuyang Mao; Furong Ye; Xiang He; Zhonglin Zu; Shaowei Cai; |
| 149 | Toward Structure Fairness in Dynamic Graph Embedding: A Trend-aware Dual Debiasing Approach Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We first identify biased structural evolutions in a dynamic graph based on the evolving trend of vertex degree and then propose FairDGE, the first structurally Fair Dynamic Graph Embedding algorithm. |
Yicong Li; Yu Yang; Jiannong Cao; Shuaiqi Liu; Haoran Tang; Guandong Xu; |
| 150 | Improving Robustness of Hyperbolic Neural Networks By Lipschitz Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we conduct a rigorous Lipschitz analysis for HNNs and propose using Lipschitz regularization as a novel strategy to enhance their robustness. |
Yuekang Li; Yidan Mao; Yifei Yang; Dongmian Zou; |
| 151 | ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In the realm of graph learning, the continuous emergence of new graphs and the challenges of human labeling also amplify the necessity for zero-shot transfer learning, driving the exploration of approaches that can generalize across diverse graph data without necessitating dataset-specific and label-specific fine-tuning. In this study, we extend such paradigms to Zero-shot transferability in Graphs by introducing ZeroG, a new framework tailored to enable cross-dataset generalization. |
Yuhan Li; Peisong Wang; Zhixun Li; Jeffrey Xu Yu; Jia Li; |
| 152 | Rethinking Fair Graph Neural Networks from Re-balancing Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose FairGB, Fair Graph Neural Network via re-Balancing, which mitigates the unfairness of GNNs by group balancing. |
Zhixun Li; Yushun Dong; Qiang Liu; Jeffrey Xu Yu; |
| 153 | Customizing Graph Neural Network for CAD Assembly Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, present recommender systems for CAD assembly modeling adopt fixed GNN architectures, which may be sub-optimal for different manufacturers with different data distribution. Therefore, to customize a well-suited recommender system for different manufacturers, we propose a novel neural architecture search (NAS) framework, dubbed CusGNN, which can design data-specific GNN automatically. |
Fengqi Liang; Huan Zhao; Yuhan Quan; Wei Fang; Chuan Shi; |
| 154 | Image Similarity Using An Ensemble of Context-Sensitive Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we present a more intuitive approach to build and compare image similarity models based on labelled data in the form of A:R vs B:R, i.e., determining if an image A is closer to a reference image R than another image B. |
Zukang Liao; Min Chen; |
| 155 | When Box Meets Graph Neural Network in Tag-aware Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, defect still exists as these approaches are incapable of capturing high-order neighbor signals, i.e., semantic-rich multi-hop relations within the user-tag-item tripartite graph, which severely limits the effectiveness of user modeling. To deal with this challenge, in this paper, we propose a novel framework, called BoxGNN, to perform message aggregation via combinations of logical operations, thereby incorporating high-order signals. |
Fake Lin; Ziwei Zhao; Xi Zhu; Da Zhang; Shitian Shen; Xueying Li; Tong Xu; Suojuan Zhang; Enhong Chen; |
| 156 | MulSTE: A Multi-view Spatio-temporal Learning Framework with Heterogeneous Event Fusion for Demand-supply Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose MulSTE, a Multi-view Spatio-Temporal learning framework with heterogeneous Event fusion. |
Li Lin; Zhiqiang Lu; Shuai Wang; Yunhuai Liu; Zhiqing Hong; Haotian Wang; Shuai Wang; |
| 157 | PSMC: Provable and Scalable Algorithms for Motif Conductance Based Graph Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Besides, expensive spectral clustering or local graph diffusion on the edge-weighted graph also makes existing methods unable to handle massive graphs with millions of nodes. To overcome these dilemmas, we propose a Provable and Scalable Motif Conductance algorithm PSMC, which has a fixed and motif-independent approximation ratio for any motif. |
Longlong Lin; Tao Jia; Zeli Wang; Jin Zhao; Rong-Hua Li; |
| 158 | Robust Auto-Bidding Strategies for Online Advertising Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address this challenge, we conducted a comprehensive analysis of the process by which DSPs obtain winning price information, and abstracted two types of uncertainties from it: known uncertainty and unknown uncertainty. Based on these uncertainties, we proposed two levels of robust bidding strategies: Robust Bidding for Censorship (RBC) and Robust Bidding for Distribution Shift (RBDS), which offer guarantees for the surplus in the worst-case scenarios under uncertain conditions. |
Qilong Lin; Zhenzhe Zheng; Fan Wu; |
| 159 | Bridging Items and Language: A Transition Paradigm for Large Language Model-Based Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, prior generation grounding methods might generate invalid identifiers, thus misaligning with in-corpus items. To address these issues, we propose a novel Transition paradigm for LLM-based Recommender (named TransRec) to bridge items and language. |
Xinyu Lin; Wenjie Wang; Yongqi Li; Fuli Feng; See-Kiong Ng; Tat-Seng Chua; |
| 160 | On The Convergence of Zeroth-Order Federated Tuning for Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, the intensive memory requirements for fine-tuning LLMs pose significant challenges, especially when deploying on clients with limited computational resources. To circumvent this, we explore the novel integration of Memory-efficient Zeroth-Order Optimization within a federated setting, a synergy we term as FedMeZO. |
Zhenqing Ling; Daoyuan Chen; Liuyi Yao; Yaliang Li; Ying Shen; |
| 161 | CONFIDE: Contextual Finite Difference Modelling of PDEs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a method for inferring an explicit PDE from a data sample generated by previously unseen dynamics, based on a learned context. |
Ori Linial; Orly Avner; Dotan Di Castro; |
| 162 | CASA: Clustered Federated Learning with Asynchronous Clients Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we present CASA, a novel CFL scheme for Clustering-Aggregation Synergy under Asynchrony. |
Boyi Liu; Yiming Ma; Zimu Zhou; Yexuan Shi; Shuyuan Li; Yongxin Tong; |
| 163 | FAST: An Optimization Framework for Fast Additive Segmentation in Transparent ML Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present FAST, an optimization framework for fast additive segmentation. |
Brian Liu; Rahul Mazumder; |
| 164 | TDNetGen: Empowering Complex Network Resilience Prediction with Generative Augmentation of Topology and Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: On the other hand, data-driven approaches frequently encounter the challenge of insufficient labeled data, a predicament commonly observed in real-world scenarios. In this paper, we introduce a novel resilience prediction framework for complex networks, designed to tackle this issue through generative data augmentation of network topology and dynamics. |
Chang Liu; Jingtao Ding; Yiwen Song; Yong Li; |
| 165 | Fast Query of Biharmonic Distance in Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In spite of BD’s importance, efficient algorithms for the exact computation or approximation of this metric on large graphs remain notably absent. In this work, we provide several algorithms to estimate BD, building on a novel formulation of this metric. |
Changan Liu; Ahad N. Zehmakan; Zhongzhi Zhang; |
| 166 | Multi-Task Learning for Routing Problem with Cross-Problem Zero-Shot Generalization Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we make a first attempt to tackle the crucial challenge of cross-problem generalization in NCO. |
Fei Liu; Xi Lin; Zhenkun Wang; Qingfu Zhang; Tong Xialiang; Mingxuan Yuan; |
| 167 | Asymmetric Beta Loss for Evidence-Based Safe Semi-Supervised Multi-Label Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a safe semi-supervised multi-label learning framework based on the theory of evidential deep learning (EDL), with the goal of achieving robust and effective unlabeled data exploitation. |
Hao-Zhe Liu; Ming-Kun Xie; Chen-Chen Zong; Sheng-Jun Huang; |
| 168 | An Unsupervised Learning Framework Combined with Heuristics for The Maximum Minimal Cut Problem Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Moreover, as a CO problem, it is also a daunting task for machine learning, especially without labeled instances. To deal with these problems, this work proposes an unsupervised learning framework combined with heuristics for MMCP that can provide valid and high-quality solutions. |
Huaiyuan Liu; Xianzhang Liu; Donghua Yang; Hongzhi Wang; Yingchi Long; Mengtong Ji; Dongjing Miao; Zhiyu Liang; |
| 169 | ACER: Accelerating Complex Event Recognition Via Two-Phase Filtering Under Range Bitmap-Based Indexes Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, prior index-based approaches suffer from significant I/O and sorting overhead when dealing with high predicate selectivity or long query window (common in real-world applications), which leads to high query latency. To address this issue, we propose ACER, a Range Bitmap-based index, to accelerate CER. |
Shizhe Liu; Haipeng Dai; Shaoxu Song; Meng Li; Jingsong Dai; Rong Gu; Guihai Chen; |
| 170 | BadSampler: Harnessing The Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We formulate the attack as an optimization problem and present two elegant adversarial sampling strategies, Top-k sampling, and meta-sampling, to approximately solve it. |
Yi Liu; Cong Wang; Xingliang Yuan; |
| 171 | Probabilistic Attention for Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In response, this work introduces a fresh perspective to elucidate the attention mechanism in SR. |
Yuli Liu; Christian Walder; Lexing Xie; Yiqun Liu; |
| 172 | Revisiting Modularity Maximization for Graph Clustering: A Contrastive Learning Perspective Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we dig into the hidden success of modularity maximization for graph clustering. |
Yunfei Liu; Jintang Li; Yuehe Chen; Ruofan Wu; Ericbk Wang; Jing Zhou; Sheng Tian; Shuheng Shen; Xing Fu; Changhua Meng; Weiqiang Wang; Liang Chen; |
| 173 | Dataset Condensation for Time Series Classification Via Dual Domain Matching Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose a novel framework named Dataset Condensation for Time Series Classification via Dual Domain Matching (CondTSC) which focuses on the time series classification dataset condensation task. |
Zhanyu Liu; Ke Hao; Guanjie Zheng; Yanwei Yu; |
| 174 | Graph Data Condensation Via Self-expressive Graph Structure Reconstruction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: They could not explicitly leverage the information of the original graph structure and failed to construct an interpretable graph structure for the synthetic dataset. To address these issues, we introduce a novel framework named Graph Data Condensation via Self-expressive Graph Structure Reconstruction (GCSR). |
Zhanyu Liu; Chaolv Zeng; Guanjie Zheng; |
| 175 | Generative Pretrained Hierarchical Transformer for Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Secondly, the one-step generation schema is widely followed, which necessitates a customized forecasting head and overlooks the temporal dependencies in the output series, and also leads to increased training costs under different horizon length settings. To address these issues, we propose a novel generative pretrained hierarchical transformer architecture for forecasting, named GPHT. |
Zhiding Liu; Jiqian Yang; Mingyue Cheng; Yucong Luo; Zhi Li; |
| 176 | AIM: Attributing, Interpreting, Mitigating Data Unfairness Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Grounding on the existing fairness notions, we lay out a sample bias criterion and propose practical algorithms for measuring and countering sample bias. |
Zhining Liu; Ruizhong Qiu; Zhichen Zeng; Yada Zhu; Hendrik Hamann; Hanghang Tong; |
| 177 | Diffusion-Based Cloud-Edge-Device Collaborative Learning for Next POI Recommendations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, these methods often suffer from computational strain on devices and struggle to adapt to new users and regions. This paper introduces a novel collaborative learning framework, Diffusion-Based Cloud-Edge-Device Collaborative Learning for Next POI Recommendations (DCPR), leveraging the diffusion model known for its success across various domains. |
Jing Long; Guanhua Ye; Tong Chen; Yang Wang; Meng Wang; Hongzhi Yin; |
| 178 | High-Dimensional Distributed Sparse Classification with Scalable Communication-Efficient Global Updates Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, existing versions of these methods experience multiple shortcomings as the data size becomes massive, including diverging updates and efficiently handling sparsity. In this work we develop solutions to these problems which enable us to learn a communication-efficient distributed logistic regression model even beyond millions of features. |
Fred Lu; Ryan R. Curtin; Edward Raff; Francis Ferraro; James Holt; |
| 179 | Neural Collapse Inspired Debiased Representation Learning for Min-max Fairness Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This indicates the sub-optimal performance in minority groups stems from less separable representations, rather than classifiers. To tackle this issue, we introduce a novel strategy that incorporates a frozen classifier to directly enhance representation. |
Shenyu Lu; Junyi Chai; Xiaoqian Wang; |
| 180 | AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, these methods face significant challenges in situations with insufficient training data and incomplete test data, limiting their applicability in real-world applications. To address these challenges, we propose AdaGMLP, an AdaBoosting GNN-to-MLP Knowledge Distillation framework. |
Weigang Lu; Ziyu Guan; Wei Zhao; Yaming Yang; |
| 181 | FUGNN: Harmonizing Fairness and Utility in Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we re-examine fairness through the lens of spectral graph theory, aiming to reconcile fairness and utility within the framework of spectral graph learning. |
Renqiang Luo; Huafei Huang; Shuo Yu; Zhuoyang Han; Estrid He; Xiuzhen Zhang; Feng Xia; |
| 182 | Learning Multi-view Molecular Representations with Structured and Unstructured Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, existing works fall short in learning multi-view molecular representations, due to challenges in explicitly incorporating view information and handling molecular knowledge from heterogeneous sources. To address these issues, we present MV-Mol, a molecular representation learning model that harvests multi-view molecular expertise from chemical structures, unstructured knowledge from biomedical texts, and structured knowledge from knowledge graphs. |
Yizhen Luo; Kai Yang; Massimo Hong; Xing Yi Liu; Zikun Nie; Hao Zhou; Zaiqing Nie; |
| 183 | Cross-Context Backdoor Attacks Against Graph Prompt Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce CrossBA, the first cross-context backdoor attack against GPL, which manipulates only the pretraining phase without requiring knowledge of downstream applications. |
Xiaoting Lyu; Yufei Han; Wei Wang; Hangwei Qian; Ivor Tsang; Xiangliang Zhang; |
| 184 | Low Rank Multi-Dictionary Selection at Scale Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Hence, an important problem that we address in this paper is: How to scale multi-dictionary coding for large dictionaries and datasets?We propose a multi-dictionary atom selection technique for low-rank sparse coding named LRMDS. |
Boya Ma; Maxwell McNeil; Abram Magner; Petko Bogdanov; |
| 185 | PolyFormer: Scalable Node-wise Filters Via Polynomial Graph Transformer Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose a scalable node-wise filter, PolyAttn. |
Jiahong Ma; Mingguo He; Zhewei Wei; |
| 186 | Handling Varied Objectives By Online Decision Making Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose the VaRons algorithm, which estimates the action-wise performance on each sub-objective and adaptively selects decisions according to the dynamic requirements on different sub-objectives. |
Lanjihong Ma; Zhen-Yu Zhang; Yao-Xiang Ding; Zhi-Hua Zhou; |
| 187 | Scalable Differentiable Causal Discovery in The Presence of Latent Confounders with Skeleton Posterior Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The key insight in this paper is that the causal skeleton, which is the undirected version of the causal graph, has potential for improving accuracy and reducing the search space of the optimization procedure, thereby enhancing the performance of differentiable causal discovery. |
Pingchuan Ma; Rui Ding; Qiang Fu; Jiaru Zhang; Shuai Wang; Shi Han; Dongmei Zhang; |
| 188 | Graph Anomaly Detection with Few Labels: A Data-Centric Approach Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: From the insights, we propose a diffusion-based graph generation method to synthesize training nodes, which can be promptly integrated to work with existing anomaly detectors. |
Xiaoxiao Ma; Ruikun Li; Fanzhen Liu; Kaize Ding; Jian Yang; Jia Wu; |
| 189 | FLAIM: AIM-based Synthetic Data Generation in The Federated Setting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we initiate the study of federated synthetic tabular data generation. |
Samuel Maddock; Graham Cormode; Carsten Maple; |
| 190 | A Uniformly Bounded Correlation Function for Spatial Point Patterns Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This approach is useful for constructing null hypothesis tests, but Ripley’s K and its variants are less suitable as quantitative effect sizes because their ranges and expected values generally depend on the scale or the size of the region in which the pattern is observed. To address this, we propose a new function that behaves like a correlation coefficient for point patterns: it is tightly bounded by -1 and 1, with a value of -1 corresponding to a maximally dispersed arrangement of points, 0 indicating complete spatial randomness, and 1 representing maximal clustering. |
Evgenia Martynova; Johannes Textor; |
| 191 | Fair Column Subset Selection Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose a deterministic leverage-score sampling strategy for the fair setting and show that sampling a column subset of minimum size becomes NP-hard in the presence of two groups. |
Antonis Matakos; Bruno Ordozgoiti; Suhas Thejaswi; |
| 192 | Interpretable Transformer Hawkes Processes: Unveiling Complex Interactions in Social Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: These models encounter challenges in capturing interactions among users or groups and often rely on parameterized extrapolation methods when modeling intensity over non-event intervals, limiting their capacity to capture intricate intensity patterns, particularly beyond observed events. To address these challenges, this study proposes modifications to Transformer Hawkes processes (THP), leading to the development of interpretable Transformer Hawkes processes (ITHP). |
Zizhuo Meng; Ke Wan; Yadong Huang; Zhidong Li; Yang Wang; Feng Zhou; |
| 193 | Scaling Training Data with Lossy Image Compression Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Given a dataset of digital images, the number of bits L to store each of them can be further reduced using lossy data compression. This, however, can degrade the quality of the model trained on such images, since each example has lower resolution.In order to capture this trade-off and optimize storage of training data, we propose a ‘storage scaling law’ that describes the joint evolution of test error with sample size and number of bits per image. |
Katherine L Mentzer; Andrea Montanari; |
| 194 | Learning Causal Networks from Episodic Data Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To in practice discover the causal model progressively over time, we propose the CONTINENT algorithm which, taking inspiration from continual learning, discovers the causal model in an online fashion without having to re-learn the model upon arrival of each new episode. |
Osman Mian; Sarah Mameche; Jilles Vreeken; |
| 195 | Quantifying and Estimating The Predictability Upper Bound of Univariate Numeric Time Series Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We call the intrinsic predictability the predictability upper bound �imax and propose a novel method for quantifying and estimating it for univariate numeric time series. |
Jamal Mohammed; Michael H. B\{o}hlen; Sven Helmer; |
| 196 | Money Never Sleeps: Maximizing Liquidity Mining Yields in Decentralized Finance Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To tackle YMLM, we propose two algorithms, namely YMLM_GD and YMLM_SK, with parameterized approximation ratios. |
Wangze Ni; Zhao Yiwei; Weijie Sun; Lei Chen; Peng Cheng; Chen Jason Zhang; Xuemin Lin; |
| 197 | ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Leveraging the strengths of both two paradigms, we demonstrate a low rankness-induced Transformer to achieve a balance between strong inductive bias and high expressivity. |
Tong Nie; Guoyang Qin; Wei Ma; Yuewen Mei; Jian Sun; |
| 198 | Improving The Consistency in Cross-Lingual Cross-Modal Retrieval with 1-to-K Contrastive Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: The methods with cross-modal style suffer from the inter-modal optimization direction bias, resulting in inconsistent rank across languages within each instance, which cannot be reflected by Recall@K. To solve these problems, we propose a simple but effective 1-to-K contrastive learning method, which treats each language equally and eliminates error propagation and optimization bias. |
Zhijie Nie; Richong Zhang; Zhangchi Feng; Hailang Huang; Xudong Liu; |
| 199 | CheatAgent: Attacking LLM-Empowered Recommender Systems Via LLM Agent Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: On the other hand, LLMs provide unprecedented opportunities to serve as attack agents to attack RecSys because of their impressive capability in simulating human-like decision-making processes. Therefore, in this paper, we propose a novel attack framework called CheatAgent by harnessing the human-like capabilities of LLMs, where an LLM-based agent is developed to attack LLM-Empowered RecSys. |
Liang-bo Ning; Shijie Wang; Wenqi Fan; Qing Li; Xin Xu; Hao Chen; Feiran Huang; |
| 200 | Mining of Switching Sparse Networks for Missing Value Imputation in Multivariate Time Series Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Here, we propose a missing value imputation method for multivariate time series, namely MissNet, that is designed to exploit temporal dependency with a state-space model and inter-correlation by switching sparse networks. |
Kohei Obata; Koki Kawabata; Yasuko Matsubara; Yasushi Sakurai; |
| 201 | Reliable Confidence Intervals for Information Retrieval Evaluation Using Generative A.I Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose two methods based on prediction-powered inference and conformal risk control that utilize computer-generated relevance annotations to place reliable confidence intervals (CIs) around IR evaluation metrics. |
Harrie Oosterhuis; Rolf Jagerman; Zhen Qin; Xuanhui Wang; Michael Bendersky; |
| 202 | Ontology Enrichment for Effective Fine-grained Entity Typing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we propose \o{}urs, where we (1) enrich each node in the ontology structure with two categories of extra information:instance information for training sample augmentation andtopic information to relate types with contexts, and (2) develop a coarse-to-fine typing algorithm that exploits the enriched information by training an entailment model with contrasting topics and instance-based augmented training samples. |
Siru Ouyang; Jiaxin Huang; Pranav Pillai; Yunyi Zhang; Yu Zhang; Jiawei Han; |
| 203 | Fast Multidimensional Partial Fourier Transform with Automatic Hyperparameter Selection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We provide a rigorous proof for the explicit reformulation of the original optimization problem of Auto-MPFT, demonstrating the process that converts it into a well-established unconstrained convex optimization problem. |
Yong-chan Park; Jongjin Kim; U Kang; |
| 204 | BTTackler: A Diagnosis-based Framework for Efficient Deep Learning Hyperparameter Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose Bad Trial Tackler (BTTackler), a novel HPO framework that introduces training diagnosis to identify training problems automatically and hence tackles bad trials. |
Zhongyi Pei; Zhiyao Cen; Yipeng Huang; Chen Wang; Lin Liu; Philip Yu; Mingsheng Long; Jianmin Wang; |
| 205 | Scalable Rule Lists Learning with Sampling Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present a novel and scalable approach to learn nearly optimal rule lists from large datasets. |
Leonardo Pellegrina; Fabio Vandin; |
| 206 | CoMAL: Contrastive Active Learning for Multi-Label Text Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Although multi-label active learning provides a cost-effective solution, it still faces two major challenges: (i) constructing decent feature space to distinguish the confusing semantics of different labels; (ii) defining proper sampling criteria to measure a sample’s joint effect over the entire label space. To bridge these gaps, we propose a Contrastive Multi-label Active Learning framework (CoMAL) that gives an effective data acquisition strategy. |
Cheng Peng; Haobo Wang; Ke Chen; Lidan Shou; Chang Yao; Runze Wu; Gang Chen; |
| 207 | TSC: A Simple Two-Sided Constraint Against Over-Smoothing Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Aiming at tackling both causes of over-smoothing in one shot, we introduce a simple Two-Sided Constraint (TSC) for GCNs, comprising two straightforward yet potent techniques: random masking and contrastive constraint. |
Furong Peng; Kang Liu; Xuan Lu; Yuhua Qian; Hongren Yan; Chao Ma; |
| 208 | How Powerful Is Graph Filtering for Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We theoretically show that linear GCN (LGCN) that is effective on collaborative filtering (CF) cannot generate arbitrary embeddings, implying the possibility that optimal data representation might be unreachable.To tackle the first limitation, we show close relation between noise distribution and the sharpness of spectrum where a sharper spectral distribution is more desirable causing data noise to be separable from important features without training. Based on this observation, we propose a generalized graph normalization (G2N) with hyperparameters adjusting the sharpness of spectral distribution in order to redistribute data noise to assure that it can be removed by graph filtering without training. |
Shaowen Peng; Xin Liu; Kazunari Sugiyama; Tsunenori Mine; |
| 209 | Fredformer: Frequency Debiased Transformer for Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we undertake empirical analyses to understand this bias and discover that frequency bias results from the model disproportionately focusing on frequency features with higher energy. Based on our analysis, we formulate this bias and propose Fredformer, a Transformer-based framework designed to mitigate frequency bias by learning features equally across different frequency bands. |
Xihao Piao; Zheng Chen; Taichi Murayama; Yasuko Matsubara; Yasushi Sakurai; |
| 210 | CASH Via Optimal Diversity for Ensemble Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We explore a theoretically sound framework that describes the relationship between pair-wise diversity and ensemble performance, which allows our Bayesian optimization framework Optimal Diversity Bayesian Optimization (OptDivBO) to directly and efficiently minimize ensemble generalization error. |
Pranav Poduval; Sanjay Kumar Patnala; Gaurav Oberoi; Nitish Srivasatava; Siddhartha Asthana; |
| 211 | Unifying Evolution, Explanation, and Discernment: A Generative Approach for Dynamic Graph Counterfactuals Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present GRACIE (Graph Recalibration and Adaptive Counterfactual Inspection and Explanation), a novel approach for generative classification and counterfactual explanations of dynamically changing graph data. |
Bardh Prenkaj; Mario Villaiz\'{a}n-Vallelado; Tobias Leemann; Gjergji Kasneci; |
| 212 | QSketch: An Efficient Sketch for Weighted Cardinality Estimation in Streams Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Unlike traditional cardinality estimation, limited research exists on weighted cardinality, with current methods requiring substantial memory and computational resources, challenging for devices with limited capabilities and real-time applications like anomaly detection. To address these issues, we propose QSketch, a memory-efficient sketch method for estimating weighted cardinality in streams. |
Yiyan Qi; Rundong Li; Pinghui Wang; Yufang Sun; Rui Xing; |
| 213 | Reimagining Graph Classification from A Prototype View with Optimal Transport: Algorithm and Theorem Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Furthermore, the graph classification decision process based on GNNs resembles a black box and lacks sufficient transparency. The non-linear classifier following the GNNs also defaults to the assumption that each class is represented by a single vector, thereby limiting the diversity of intra-class representations.To address these issues, we propose a novel prototype-based graph classification framework that introduces the Fused Gromov-Wasserstein (FGW) distance in Optimal Transport (OT) as the similarity measure. |
Chen Qian; Huayi Tang; Hong Liang; Yong Liu; |
| 214 | ORCDF: An Oversmoothing-Resistant Cognitive Diagnosis Framework for Student Learning in Online Education Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, this paper proposes an oversmoothing-resistant cognitive diagnosis framework (ORCDF) to enhance existing CDMs by utilizing response signals in the learning part. |
Hong Qian; Shuo Liu; Mingjia Li; Bingdong Li; Zhi Liu; Aimin Zhou; |
| 215 | Pre-train and Refine: Towards Higher Efficiency in K-Agnostic Community Detection Without Quality Degradation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose PRoCD (Pre-training \& Refinement fOr Community Detection), a simple yet effective method that reformulates K-agnostic CD as the binary node pair classification. |
Meng Qin; Chaorui Zhang; Yu Gao; Weixi Zhang; Dit-Yan Yeung; |
| 216 | A Fast Exact Algorithm to Enumerate Maximal Pseudo-cliques in Large Sparse Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present an exact algorithm named Fast Pseudo-Clique Enumerator (FPCE). |
Ahsanur Rahman; Kalyan Roy; Ramiza Maliha; Townim Faisal Chowdhury; |
| 217 | RHiOTS: A Framework for Evaluating Hierarchical Time Series Forecasting Algorithms Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce the Robustness of Hierarchically Organized Time Series (RHiOTS) framework, designed to assess the robustness of hierarchical time series forecasting models and algorithms on real-world datasets. |
Luis Roque; Carlos Soares; Lu\'{\i}s Torgo; |
| 218 | CoSLight: Co-optimizing Collaborator Selection and Decision-making to Enhance Traffic Signal Control Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, quite a lot of congestion, even some wide-range congestion, is caused by non-neighbors failing to collaborate. To address these issues, we propose to separate the collaborator selection as a second policy to be learned, concurrently being updated with the original signal-controlling policy. |
Jingqing Ruan; Ziyue Li; Hua Wei; Haoyuan Jiang; Jiaming Lu; Xuantang Xiong; Hangyu Mao; Rui Zhao; |
| 219 | A Novel Feature Space Augmentation Method to Improve Classification Performance and Evaluation Reliability Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: It remains to be seen whether augmentation can be applied to improve the overall performance while maintaining stability, especially with a limited number of samples. In this paper, we present a novel feature-space augmentation technique that can be applied to high-dimensional data for classification tasks and address these issues. |
Sakhawat Hossain Saimon; Tanzira Najnin; Jianhua Ruan; |
| 220 | LARP: Language Audio Relational Pre-training for Cold-Start Playlist Continuation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Furthermore, even the musical state-of-the-art content modules are either (1) incompatible with the cold-start setting or (2) unable to effectively integrate cross-modal and relational signals. In this paper, we introduce LARP, a multi-modal cold-start playlist continuation model, to effectively overcome these limitations. |
Rebecca Salganik; Xiaohao Liu; Yunshan Ma; Jian Kang; Tat-Seng Chua; |
| 221 | Scalable Temporal Motif Densest Subnetwork Discovery Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Identifying temporal motifs is an extremely challenging task, and thus, efficient methods are required. To address this challenge, we design two novel randomized approximation algorithms with rigorous probabilistic guarantees that provide high-quality solutions. |
Ilie Sarpe; Fabio Vandin; Aristides Gionis; |
| 222 | DPHGNN: A Dual Perspective Hypergraph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we analyze the impact of change in hypergraph topology on the suboptimal performance of HGNNs and propose DPHGNN, a novel dual-perspective HGNN that introduces equivariant operator learning to capture lower-order semantics by inducing topology-aware spatial and spectral inductive biases. |
Siddhant Saxena; Shounak Ghatak; Raghu Kolla; Debashis Mukherjee; Tanmoy Chakraborty; |
| 223 | Self-Supervised Learning of Time Series Representation Via Diffusion Process and Imputation-Interpolation-Forecasting Mask Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, they primarily target specific application scenarios like imputation and forecasting, leaving a gap in leveraging diffusion models for generic TSRL. Our work, Time Series Diffusion Embedding (TSDE), bridges this gap as the first diffusion-based SSL TSRL approach. |
Zineb Senane; Lele Cao; Valentin Leonhard Buchner; Yusuke Tashiro; Lei You; Pawel Andrzej Herman; Mats Nordahl; Ruibo Tu; Vilhelm von Ehrenheim; |
| 224 | Self-Explainable Temporal Graph Networks Based on Graph Information Bottleneck Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose a novel built-in explanation framework for temporal graphs, called Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck (TGIB). |
Sangwoo Seo; Sungwon Kim; Jihyeong Jung; Yoonho Lee; Chanyoung Park; |
| 225 | NeuroCut: A Neural Approach for Robust Graph Partitioning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we develop NeuroCut with two key innovations over previous methodologies. |
Rishi Shah; Krishnanshu Jain; Sahil Manchanda; Sourav Medya; Sayan Ranu; |
| 226 | Certified Robustness on Visual Graph Matching Via Searching Optimal Smoothing Range Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Inspired by the randomized smoothing (RS) technique, we propose the Certified Robustness based on the Optimal Smoothing Range Search (CR-OSRS) technique to fulfill the robustness guarantee for deep visual GM. |
Huaqing Shao; Lanjun Wang; Yongwei Wang; Qibing Ren; Junchi Yan; |
| 227 | Offline Imitation Learning with Model-based Reverse Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To encourage more exploration on expert-unobserved states, we propose a novel model-based framework, called offline Imitation Learning with Self-paced Reverse Augmentation (SRA). |
Jie-Jing Shao; Hao-Sen Shi; Lan-Zhe Guo; Yu-Feng Li; |
| 228 | STEMO: Early Spatio-temporal Forecasting with Multi-Objective Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose an early spatio-temporal forecasting model based on Multi-Objective reinforcement learning that can either implement an optimal policy given a preference or infer the preference based on a small number of samples. |
Wei Shao; Yufan Kang; Ziyan Peng; Xiao Xiao; Lei Wang; Yuhui Yang; Flora D. Salim; |
| 229 | Capturing Homogeneous Influence Among Students: Hypergraph Cognitive Diagnosis for Intelligent Education Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, this paper proposes a hypergraph cognitive diagnosis model (HyperCDM) to address these challenges and effectively capture the homogeneous influence. |
Junhao Shen; Hong Qian; Shuo Liu; Wei Zhang; Bo Jiang; Aimin Zhou; |
| 230 | Optimizing OOD Detection in Molecular Graphs: A Novel Approach with Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose to detect OOD molecules by adopting an auxiliary diffusion model-based framework, which compares similarities between input molecules and reconstructed graphs. |
Xu Shen; Yili Wang; Kaixiong Zhou; Shirui Pan; Xin Wang; |
| 231 | MSPipe: Efficient Temporal GNN Training Via Staleness-Aware Pipeline Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose MSPipe, a general and efficient framework for memory-based TGNNs that maximizes training throughput while maintaining model accuracy. |
Guangming Sheng; Junwei Su; Chao Huang; Chuan Wu; |
| 232 | Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To overcome them, we propose a novel framework to achieve efficient and long-tailed generalization, which can be termed as Candle. |
Jiang-Xin Shi; Chi Zhang; Tong Wei; Yu-Feng Li; |
| 233 | Orthogonality Matters: Invariant Time Series Representation for Out-of-distribution Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, previous models purportedly yielding domain-agnostic features continue to harbor domain-specific information, thereby diminishing their adaptability to OOD data. To address this gap, we introduce a novel model called Invariant Time Series Representation (ITSR). |
Ruize Shi; Hong Huang; Kehan Yin; Wei Zhou; Hai Jin; |
| 234 | LPFormer: An Adaptive Graph Transformer for Link Prediction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This limits the ability of existing methods to learn how to properly classify a variety of different links that may form from different factors. To address this limitation, we propose a new method, LPFormer, which attempts to adaptively learn the pairwise encodings for each link. |
Harry Shomer; Yao Ma; Haitao Mao; Juanhui Li; Bo Wu; Jiliang Tang; |
| 235 | CoLiDR: Concept Learning Using Aggregated Disentangled Representations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel method CoLiDR – which utilizes a disentangled representation learning setup for learning mutually independent generative factors and subsequently learns to aggregate the said representations into human-understandable concepts using a novel aggregation/decomposition module. |
Sanchit Sinha; Guangzhi Xiong; Aidong Zhang; |
| 236 | MAML-en-LLM: Model Agnostic Meta-Training of LLMs for Improved In-Context Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose MAML-en-LLM, a novel method for meta-training LLMs, which can learn truly generalizable parameters that not only performs well on disjointed tasks but also adapts to unseen tasks. |
Sanchit Sinha; Yuguang Yue; Victor Soto; Mayank Kulkarni; Jianhua Lu; Aidong Zhang; |
| 237 | On Early Detection of Hallucinations in Factual Question Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we explore if the artifacts associated with the model generations can provide hints that the generation will contain hallucinations. |
Ben Snyder; Marius Moisescu; Muhammad Bilal Zafar; |
| 238 | Marrying Dialogue Systems with Data Visualization: Interactive Data Visualization Generation from Natural Language Conversations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a new task named CoVis, short for Conversational text-to-Visualization, aiming at constructing DVs through a series of interactions between users and the system. |
Yuanfeng Song; Xuefang Zhao; Raymond Chi-Wing Wong; |
| 239 | Mitigating Negative Transfer in Cross-Domain Recommendation Via Knowledge Transferability Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Worse still, we argue that simple feature decomposition is insufficient for multi-domain scenarios. To bridge this gap, we propose TrineCDR, the TRIple-level kNowledge transferability Enhanced model for multi-target CDR. |
Zijian Song; Wenhan Zhang; Lifang Deng; Jiandong Zhang; Zhihua Wu; Kaigui Bian; Bin Cui; |
| 240 | Fast Computation for The Forest Matrix of An Evolving Graph Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study the problem of querying entries of the forest matrix in evolving graphs, which more accurately represent the dynamic nature of real-world networks compared to static graphs. |
Haoxin Sun; Xiaotian Zhou; Zhongzhi Zhang; |
| 241 | CrossLight: Offline-to-Online Reinforcement Learning for Cross-City Traffic Signal Control Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, in this paper, we present an innovative cross-city Traffic Signal Control (TSC) paradigm called CrossLight. |
Qian Sun; Rui Zha; Le Zhang; Jingbo Zhou; Yu Mei; Zhiling Li; Hui Xiong; |
| 242 | Dual-Assessment Driven Pruning: Iterative Optimizing Layer-wise Sparsity for Large Language Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Conventional pruning methods assess the significance of weights within individual layers and typically apply uniform sparsity levels across all layers, potentially neglecting the varying significance of each layer. To address this oversight, we first propose a dual-assessment driven pruning strategy that employs both intra-layer metric and global performance metric to comprehensively evaluate the impact of pruning. Then our method leverages an iterative optimization algorithm to find the optimal layer-wise sparsity distribution, thereby minimally impacting model performance. |
Qinghui Sun; Weilun Wang; Yanni Zhu; Shenghuan He; Hao Yi; Zehua Cai; Hong Liu; |
| 243 | Going Where, By Whom, and at What Time: Next Location Prediction Considering User Preference and Temporal Regularity Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Specifically, previous studies usually neglect the explicit user preference information entailed from human trajectories and fall short in utilizing the arrival time of next location, as a key determinant on next location. To address these limitations, we propose a Multi-Context aware Location Prediction model (MCLP) to predict next locations for individuals, where it explicitly models user preference and the next arrival time as context. |
Tianao Sun; Ke Fu; Weiming Huang; Kai Zhao; Yongshun Gong; Meng Chen; |
| 244 | DIVE: Subgraph Disagreement for Graph Out-of-Distribution Generalization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Current methodologies, including subgraph-mixup and information bottleneck approaches, have achieved partial success but struggle to overcome simplicity bias, often reinforcing spurious correlations. To tackle this, our study introduces a new learning paradigm for graph OOD issue. |
Xin Sun; Liang Wang; Qiang Liu; Shu Wu; Zilei Wang; Liang Wang; |
| 245 | Self-Supervised Denoising Through Independent Cascade Graph Augmentation for Robust Social Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Through data analysis, we discover that (1) social noise likely comes from the connected users with low preference similarity; and (2) Opinion Leaders (OLs) play a pivotal role in influence dissemination, surpassing high-similarity neighbors, regardless of their preference similarity with trusting peers. Guided by these observations, we propose a novel Self-Supervised Denoising approach through Independent Cascade Graph Augmentation, for more robust SR. |
Youchen Sun; Zhu Sun; Yingpeng Du; Jie Zhang; Yew Soon Ong; |
| 246 | Hierarchical Linear Symbolized Tree-Structured Neural Processes Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a Hierarchical Linear Symbolized Tree-structured Neural Processes (HLNPs) architecture. |
Jin yang Tai; Yi ke Guo; |
| 247 | Learning Attributed Graphlets: Predictive Graph Mining By Graphlets with Trainable Attribute Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes an interpretable classification algorithm for attributed graph data, called LAGRA (Learning Attributed GRAphlets). |
Shinji Tajima; Ren Sugihara; Ryota Kitahara; Masayuki Karasuyama; |
| 248 | HiGPT: Heterogeneous Graph Language Model Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To tackle those challenges, we propose HiGPT, a general large graph model with Heterogeneous graph instruction-tuning paradigm. |
Jiabin Tang; Yuhao Yang; Wei Wei; Lei Shi; Long Xia; Dawei Yin; Chao Huang; |
| 249 | Towards Robust Recommendation Via Decision Boundary-aware Graph Contrastive Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, most existing GCL models rely on heuristic approaches and usually assume entity independence when constructing contrastive views. We argue that these methods struggle to strike a balance between semantic invariance and view hardness across the dynamic training process, both of which are critical factors in graph contrastive learning.To address the above issues, we propose a novel GCL-based recommendation framework RGCL, which effectively maintains the semantic invariance of contrastive pairs and dynamically adapts as the model capability evolves through the training process. |
Jiakai Tang; Sunhao Dai; Zexu Sun; Xu Chen; Jun Xu; Wenhui Yu; Lantao Hu; Peng Jiang; Han Li; |
| 250 | EcoVal: An Efficient Data Valuation Framework for Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce an efficient data valuation framework EcoVal, to estimate the value of data for machine learning models in a fast and practical manner. |
Ayush Tarun; Vikram Chundawat; Murari Mandal; Hong Ming Tan; Bowei Chen; Mohan Kankanhalli; |
| 251 | Causal Estimation of Exposure Shifts with Neural Networks and An Application to Inform Air Quality Standards in The US Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce Targeted Regularization for Exposure Shifts with Neural Networks (TRESNET), a method to estimate SRFs with robustness and efficiency guarantees. |
Mauricio Tec; Kevin Josey; Oladimeji Mudele; Francesca Dominici; |
| 252 | URRL-IMVC: Unified and Robust Representation Learning for Incomplete Multi-View Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, they either neglect valuable complementary information by focusing only on consensus between views or provide unreliable recovered views due to the absence of supervision. To address these limitations, we propose a novel Unified and Robust Representation Learning for Incomplete Multi-View Clustering (URRL-IMVC). |
Ge Teng; Ting Mao; Chen Shen; Xiang Tian; Xuesong Liu; Yaowu Chen; Jieping Ye; |
| 253 | Latent Diffusion-based Data Augmentation for Continuous-Time Dynamic Graph Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, these methods often demand substantial domain expertise for parameter tuning and lack theoretical guarantees for augmentation efficacy. To address these issues, we propose Conda, a novel latent diffusion-based GDA method tailored for CTDGs. |
Yuxing Tian; Aiwen Jiang; Qi Huang; Jian Guo; Yiyan Qi; |
| 254 | Rotative Factorization Machines Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Firstly, they mainly model the feature interactions within a bounded order (e.g., small integer order) due to the exponential growth of the interaction terms. Secondly, the interaction order of each feature is often independently learned, which lacks the flexibility to capture the feature dependencies in varying contexts. To address these issues, we present Rotative Factorization Machines (RFM), based on the key idea that represents each feature as a polar angle in the complex plane. |
Zhen Tian; Yuhong Shi; Xiangkun Wu; Wayne Xin Zhao; Ji-Rong Wen; |
| 255 | Online Drift Detection with Maximum Concept Discrepancy Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose MCD-DD, a novel concept drift detection method based on maximum concept discrepancy, inspired by the maximum mean discrepancy. |
Ke Wan; Yi Liang; Susik Yoon; |
| 256 | Flexible Graph Neural Diffusion with Latent Class Representation Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose the Flexible Graph Neural Diffusion (FGND) model, incorporating latent class representation to address the misalignment between graph topology and node features. |
Liangtian Wan; Huijin Han; Lu Sun; Zixun Zhang; Zhaolong Ning; Xiaoran Yan; Feng Xia; |
| 257 | STONE: A Spatio-temporal OOD Learning Framework Kills Both Spatial and Temporal Shifts Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To tackle the challenges of spatio-temporal shift, we propose a framework called STONE by learning invariable node dependencies, which achieve stable performance in variable environments. |
Binwu Wang; Jiaming Ma; Pengkun Wang; Xu Wang; Yudong Zhang; Zhengyang Zhou; Yang Wang; |
| 258 | Provable Adaptivity of Adam Under Non-uniform Smoothness Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present the first convergence analysis of RR Adam without the bounded smoothness assumption. |
Bohan Wang; Yushun Zhang; Huishuai Zhang; Qi Meng; Ruoyu Sun; Zhi-Ming Ma; Tie-Yan Liu; Zhi-Quan Luo; Wei Chen; |
| 259 | Pre-Training with Transferable Attention for Addressing Market Shifts in Cross-Market Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, CMR experiences market shifts, leading to differences in item popularity and user preferences among different markets. This study focuses on cross-market sequential recommendation (CMSR) and proposes the Cross-market Attention Transferring with Sequential Recommendation (CAT-SR) framework to address these challenges and market shifts. |
Chen Wang; Ziwei Fan; Liangwei Yang; Mingdai Yang; Xiaolong Liu; Zhiwei Liu; Philip Yu; |
| 260 | Multi-Scale Detection of Anomalous Spatio-Temporal Trajectories in Evolving Trajectory Datasets Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a multi-scale model, termed MST-OATD, for anomalous streaming trajectory detection that considers both the spatial and temporal aspects of trajectories. |
Chenhao Wang; Lisi Chen; Shuo Shang; Christian S. Jensen; Panos Kalnis; |
| 261 | Global Human-guided Counterfactual Explanations for Molecular Properties Via Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we develop a novel global explanation model RLHEX for molecular property prediction. |
Danqing Wang; Antonis Antoniades; Kha-Dinh Luong; Edwin Zhang; Mert Kosan; Jiachen Li; Ambuj Singh; William Yang Wang; Lei Li; |
| 262 | Reinforced Compressive Neural Architecture Search for Versatile Adversarial Robustness Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, heuristic rules are inadequate to handle diverse adversarial attacks and different teacher network capacity. To address this key challenge, we propose Reinforced Compressive Neural Architecture Search (RC-NAS), aiming to achieve Versatile Adversarial Robustness. |
Dingrong Wang; Hitesh Sapkota; Zhiqiang Tao; Qi Yu; |
| 263 | CE-RCFR: Robust Counterfactual Regression for Consensus-Enabled Treatment Effect Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, two critical issues have long been overlooked: (1)Mini-batch sampling sensitivity (MSS) issue, where representation distribution alignment at a mini-batch level is vulnerable to poor sampling cases, such as data imbalance and outliers; (2)Inconsistent representation learning (IRL) issue, where representation learning within a unified backbone network suffers from inconsistent gradient update directions due to the distribution skew between different treatment groups. To resolve these issues, we propose CE-RCFR, a Robust CounterFactual Regression framework for Consensus-Enabled causal effect estimation, including a relaxed distribution discrepancy regularizer (RDDR) module and a consensus-enabled aggregator (CEA) module. |
Fan Wang; Chaochao Chen; Weiming Liu; Tianhao Fan; Xinting Liao; Yanchao Tan; Lianyong Qi; Xiaolin Zheng; |
| 264 | Routing Evidence for Unseen Actions in Video Moment Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we specifically consider a new problem: video moment retrieval by queries with unseen actions. |
Guolong Wang; Xun Wu; Zheng Qin; Liangliang Shi; |
| 265 | Revisiting Local PageRank Estimation on Undirected Graphs: Simple and Optimal Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a simple and optimal algorithm, BackMC, for local PageRank estimation in undirected graphs: given an arbitrary target node t in an undirected graph G comprising n nodes and m edges, BackMC accurately estimates the PageRank score of node t while assuring a small relative error and a high success probability. |
Hanzhi Wang; |
| 266 | Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite the notable success, there is very limited literature that provides a theoretical tool for characterizing the behaviors of long-tail classes in graphs and gaining insight into generalization performance in real-world scenarios. To bridge this gap, we propose a generalization bound for long-tail classification on graphs by formulating the problem in the fashion of multi-task learning, i.e., each task corresponds to the prediction of one particular class. |
Haohui Wang; Baoyu Jing; Kaize Ding; Yada Zhu; Wei Cheng; Si Zhang; Yonghui Fan; Liqing Zhang; Dawei Zhou; |
| 267 | Unsupervised Heterogeneous Graph Rewriting Attack Via Node Clustering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel unsupervised heterogeneous graph rewriting attack via node clustering (HGAC) that can effectively attack HG pre-training models without using labels. |
Haosen Wang; Can Xu; Chenglong Shi; Pengfei Zheng; Shiming Zhang; Minhao Cheng; Hongyang Chen; |
| 268 | FedNLR: Federated Learning with Neuron-wise Learning Rates Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Though effective, existing methods generally take the model as a whole, which lacks a deep understanding of how the neurons within deep classification models evolve during local training to form model drift. In this paper, we bridge this gap by performing an intuitive and theoretical analysis of the activation changes of each neuron during local training. |
Haozhao Wang; Peirong Zheng; Xingshuo Han; Wenchao Xu; Ruixuan Li; Tianwei Zhang; |
| 269 | Effective Edge-wise Representation Learning in Edge-Attributed Bipartite Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Building on an in-depth and rigorous theoretical analysis, we propose the factorized feature propagation (FFP) scheme for edge representations with adequate incorporation of long-range dependencies of edges/features without incurring tremendous computation overheads. |
Hewen Wang; Renchi Yang; Xiaokui Xiao; |
| 270 | Learning from Emergence: A Study on Proactively Inhibiting The Monosemantic Neurons of Artificial Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Monosemantic neurons tend to be sparser and have negative impacts on the performance in large models. Inspired by this insight, we propose an intuitive idea to identify monosemantic neurons and inhibit them. |
Jiachuan Wang; Shimin Di; Lei Chen; Charles Wang Wai Ng; |
| 271 | Robust Predictions with Ambiguous Time Delays: A Bootstrap Strategy Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: These delays, originating from a multitude of sources like varying data transmission dynamics, sensor interferences, and environmental changes, introduce significant complexities. Traditional Time Delay Estimation methods, which typically assume a fixed constant time delay, may not fully capture these variabilities, compromising the precision of predictive models in diverse settings.To address this issue, we introduce the Time Series Model Bootstrap (TSMB), a versatile framework designed to handle potentially varying or even nondeterministic time delays in time series modeling. |
Jiajie Wang; Zhiyuan Jerry Lin; Wen Chen; |
| 272 | A Novel Prompt Tuning for Graph Transformers: Tailoring Prompts to Graph Topologies Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a Topo-specific Graph Prompt Tuning (TGPT ), which provides topo-specific prompts tailored to the topological structures of input graphs. |
Jingchao Wang; Zhengnan Deng; Tongxu Lin; Wenyuan Li; Shaobin Ling; |
| 273 | DyPS: Dynamic Parameter Sharing in Multi-Agent Reinforcement Learning for Spatio-Temporal Resource Allocation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: There remain two primary challenges in efficient parameter sharing: (1) during the RL training process, the behavior of agents changes significantly, limiting the performance of group parameter sharing based on fixed role division decided before training; (2) the behavior of agents forms complicated action trajectories, where their role characteristics are implicit, adding difficulty to dynamically adjusting agent role divisions during the training process. In this paper, we propose Dynamic Parameter Sharing (DyPS) to solve the above challenges. |
Jingwei Wang; Qianyue Hao; Wenzhen Huang; Xiaochen Fan; Zhentao Tang; Bin Wang; Jianye Hao; Yong Li; |
| 274 | POND: Multi-Source Time Series Domain Adaptation with Information-Aware Prompt Tuning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The difficulty to evaluate learned domain-specific information. In order to tackle these challenges simultaneously, in this paper, we introduce PrOmpt-based domaiN Discrimination (POND), the first framework to utilize prompts for time series domain adaptation. |
Junxiang Wang; Guangji Bai; Wei Cheng; Zhengzhang Chen; Liang Zhao; Haifeng Chen; |
| 275 | The Snowflake Hypothesis: Training and Powering GNN with One Node One Receptive Field Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce the Snowflake Hypothesis — a novel paradigm underpinning the concept of one node, one receptive field”. |
Kun Wang; Guohao Li; Shilong Wang; Guibin Zhang; Kai Wang; Yang You; Junfeng Fang; Xiaojiang Peng; Yuxuan Liang; Yang Wang; |
| 276 | The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, or the first time, we transfer the prevailing concept of one node one receptive field to the heterophilic graph. |
Kun Wang; Guibin Zhang; Xinnan Zhang; Junfeng Fang; Xun Wu; Guohao Li; Shirui Pan; Wei Huang; Yuxuan Liang; |
| 277 | CutAddPaste: Time Series Anomaly Detection By Exploiting Abnormal Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces CutAddPaste, a novel anomaly assumption-based approach for detecting time-series anomalies. |
Rui Wang; Xudong Mou; Renyu Yang; Kai Gao; Pin Liu; Chongwei Liu; Tianyu Wo; Xudong Liu; |
| 278 | Advancing Molecule Invariant Representation Via Privileged Substructure Identification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This highlights the need for integrating this prior knowledge and ensuring the environment split compatible with molecule invariant learning. To bridge this gap, we propose a novel framework named MILI. |
Ruijia Wang; Haoran Dai; Cheng Yang; Le Song; Chuan Shi; |
| 279 | A Hierarchical and Disentangling Interest Learning Framework for Unbiased and True News Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, this paper addresses these gaps by introducing a novel framework, the Hierarchical and Disentangling Interest learning framework (HDInt). |
Shoujin Wang; Wentao Wang; Xiuzhen Zhang; Yan Wang; Huan Liu; Fang Chen; |
| 280 | DiffCrime: A Multimodal Conditional Diffusion Model for Crime Risk Map Inference Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Motivated by the impressive and realistic conditional generating power of diffusion models, in this paper, we propose a multimodal conditional diffusion method, namely, DiffCrime, to infer the crime risk map based on datasets in various domains, i.e., historical crime incidents, satellite imagery, and map imagery. |
Shuliang Wang; Xinyu Pan; Sijie Ruan; Haoyu Han; Ziyu Wang; Hanning Yuan; Jiabao Zhu; Qi Li; |
| 281 | Optimizing Long-tailed Link Prediction in Graph Neural Networks Through Structure Representation Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: After knowing the weakness of link prediction, a natural question is how can we eliminate the negative effects of the skewed long-tailed distribution on common neighbors so as to improve the performance of link prediction? Towards this end, we introduce our long-tailed framework (LTLP), which is designed to enhance the performance of tail node pairs on link prediction by increasing common neighbors. |
Yakun Wang; Daixin Wang; Hongrui Liu; Binbin Hu; Yingcui Yan; Qiyang Zhang; Zhiqiang Zhang; |
| 282 | Warming Up Cold-Start CTR Prediction By Learning Item-Specific Feature Interactions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While existing methods focus on enhancing item ID embeddings for new items within general CTR models, they tend to adopt a global feature interaction approach, often overshadowing new items with sparse data by those with abundant interactions. Addressing this, our work introduces EmerG, a novel approach that warms up cold-start CTR prediction by learning item-specific feature interaction patterns. |
Yaqing Wang; Hongming Piao; Daxiang Dong; Quanming Yao; Jingbo Zhou; |
| 283 | EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, existing generative methods typically focus solely on either behavioral or semantic aspects of item information, neglecting their complementary nature and thus resulting in limited effectiveness. To address this limitation, we introduce EAGER, a novel generative recommendation framework that seamlessly integrates both behavioral and semantic information. |
Ye Wang; Jiahao Xun; Minjie Hong; Jieming Zhu; Tao Jin; Wang Lin; Haoyuan Li; Linjun Li; Yan Xia; Zhou Zhao; Zhenhua Dong; |
| 284 | DPSW-Sketch: A Differentially Private Sketch Framework for Frequency Estimation Over Sliding Windows Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we focus on the two fundamental problems of privately (1) estimating the frequency of an arbitrary item and (2) identifying the most frequent items (i.e., heavy hitters), in the sliding window model. |
Yiping Wang; Yanhao Wang; Cen Chen; |
| 285 | AsyncET: Asynchronous Representation Learning for Knowledge Graph Entity Typing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an efficient and robust algorithm to group similar entity types together and assign a unique auxiliary relation to each group. |
Yun-Cheng Wang; Xiou Ge; Bin Wang; C.-C. Jay Kuo; |
| 286 | Unveiling Global Interactive Patterns Across Graphs: Towards Interpretable Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, graph-level tasks necessitate long-range dependencies and global interactions for advanced GNNs, deviating significantly from subgraph-specific explanations. To bridge this gap, this paper proposes a novel intrinsically interpretable scheme for graph classification, termed as Global Interactive Pattern (GIP) learning, which introduces learnable global interactive patterns to explicitly interpret decisions. |
Yuwen Wang; Shunyu Liu; Tongya Zheng; Kaixuan Chen; Mingli Song; |
| 287 | Self-Supervised Learning for Graph Dataset Condensation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Although several GDC methods have been proposed, they are all supervised and require massive labels for the graphs, while graph labels can be scarce in many practical scenarios. To fill this gap, we propose a self-supervised graph dataset condensation method called SGDC, which does not require label information. |
Yuxiang Wang; Xiao Yan; Shiyu Jin; Hao Huang; Quanqing Xu; Qingchen Zhang; Bo Du; Jiawei Jiang; |
| 288 | FedSAC: Dynamic Submodel Allocation for Collaborative Fairness in Federated Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This oversight inevitably decreases both fairness and model accuracy in practice. To address these issues, we propose FedSAC, a novel Federated learning framework with dynamic Submodel Allocation for Collaborative fairness, backed by a theoretical convergence guarantee. |
Zihui Wang; Zheng Wang; Lingjuan Lyu; Zhaopeng Peng; Zhicheng Yang; Chenglu Wen; Rongshan Yu; Cheng Wang; Xiaoliang Fan; |
| 289 | Unveiling Vulnerabilities of Contrastive Recommender Systems to Poisoning Attacks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We validate the threats of our attack model through extensive experimentation on four datasets. By shedding light on these vulnerabilities, our goal is to advance the development of more robust CL-based recommender systems. |
Zongwei Wang; Junliang Yu; Min Gao; Hongzhi Yin; Bin Cui; Shazia Sadiq; |
| 290 | From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: These are challenges that current tabular deep learning approaches have not fully tackled. Here we introduce Generative Tabular Learning (GTL), a novel framework that integrates the advanced functionalities of large language models (LLMs)-such as prompt-based zero-shot generalization and in-context learning-into tabular deep learning. |
Xumeng Wen; Han Zhang; Shun Zheng; Wei Xu; Jiang Bian; |
| 291 | Dense Subgraph Discovery Meets Strong Triadic Closure Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we apply STC to dense subgraph discovery. |
Chamalee Wickrama Arachchi; Iiro Kumpulainen; Nikolaj Tatti; |
| 292 | FedBiOT: LLM Local Fine-tuning in Federated Learning Without Full Model Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we introduce FedBiOT, a resource-efficient LLM fine-tuning approach to FL. |
Feijie Wu; Zitao Li; Yaliang Li; Bolin Ding; Jing Gao; |
| 293 | Neural Manifold Operators for Learning The Evolution of Physical Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the problem, we present Neural Manifold Operator (NMO) to learn the invariant subspace with the intrinsic dimension to parameterize infinite-dimensional underlying operators. |
Hao Wu; Kangyu Weng; Shuyi Zhou; Xiaomeng Huang; Wei Xiong; |
| 294 | Fake News in Sheep’s Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Our analysis reveals that LLM-camouflaged fake news content significantly undermines the effectiveness of state-of-the-art text-based detectors (up to 38\% decrease in F1 Score), implying a severe vulnerability to stylistic variations. To address this, we introduce SheepDog, a style-robust fake news detector that prioritizes content over style in determining news veracity. |
Jiaying Wu; Jiafeng Guo; Bryan Hooi; |
| 295 | Distributional Network of Networks for Modeling Data Heterogeneity Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Furthermore, we show that based on the TENON framework, domain adaptation and out-of-distribution generalization can be naturally formulated as transductive and inductive distribution learning problems, respectively. This motivates us to develop two instantiated algorithms (TENON-DA and TENON-OOD) of the proposed TENON framework for domain adaptation and out-of-distribution generalization. |
Jun Wu; Jingrui He; Hanghang Tong; |
| 296 | CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To further align LLMs’ reasoning to task-specific user-item interaction knowledge, we introduce collaborative retrieval-augmented LLMs, CoRAL, which directly incorporate collaborative evidence into the prompts. |
Junda Wu; Cheng-Chun Chang; Tong Yu; Zhankui He; Jianing Wang; Yupeng Hou; Julian McAuley; |
| 297 | Counterfactual Generative Models for Time-Varying Treatments Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Furthermore, in modern applications, the outcomes are high-dimensional and conventional average treatment effect estimation fails to capture disparities in individuals. To tackle these challenges, we propose a novel conditional generative framework capable of producing counterfactual samples under time-varying treatment, without the need for explicit density estimation. |
Shenghao Wu; Wenbin Zhou; Minshuo Chen; Shixiang Zhu; |
| 298 | ProCom: A Few-shot Targeted Community Detection Algorithm Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose ProCom, a novel framework that extends the pre-train, prompt” paradigm, offering a low-resource, high-efficiency, and transferable solution. |
Xixi Wu; Kaiyu Xiong; Yun Xiong; Xiaoxin He; Yao Zhang; Yizhu Jiao; Jiawei Zhang; |
| 299 | Unifying Graph Convolution and Contrastive Learning in Collaborative Filtering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Stemming from our findings, we introduce Simple Contrastive Collaborative Filtering (SCCF), a simple and effective algorithm based on a naive embedding model and a modified contrastive loss. |
Yihong Wu; Le Zhang; Fengran Mo; Tianyu Zhu; Weizhi Ma; Jian-Yun Nie; |
| 300 | DFGNN: Dual-frequency Graph Neural Network for Sign-aware Feedback Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Based on the two observations, we propose a novel model that models positive and negative feedback from a frequency filter perspective called Dual-frequency Graph Neural Network for Sign-aware Recommendation (DFGNN). |
Yiqing Wu; Ruobing Xie; Zhao Zhang; Xu Zhang; Fuzhen Zhuang; Leyu Lin; Zhanhui Kang; Yongjun Xu; |
| 301 | Cost-Efficient Fraud Risk Optimization with Submodularity in Insurance Claim Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, this paper proposes a framework named cost-efficient fraud risk optimization with submodularity (CEROS) to optimize the process of fraud risk verification. |
Yupeng Wu; Zhibo Zhu; Chaoyi Ma; Hong Qian; Xingyu Lu; Yangwenhui Zhang; Xiaobo Qin; Binjie Fei; Jun Zhou; Aimin Zhou; |
| 302 | A Deep Prediction Framework for Multi-Source Information Via Heterogeneous GNN Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a novel extensible framework, coined as HIF, for effective popularity prediction in OSNs with four original contributions. First, HIF adopts a soft partition of users and time intervals to better learn users’ behavioral preferences over time. |
Zhen Wu; Jingya Zhou; Jinghui Zhang; Ling Liu; Chizhou Huang; |
| 303 | Fast Computation of Kemeny’s Constant for Directed Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Existing approximation algorithms either leverage properties exclusive to undirected graphs or involve inefficient simulation, leaving room for further optimization. To address these limitations for directed graphs, we propose two novel approximation algorithms for estimating Kemeny’s constant on directed graphs with theoretical error guarantees. |
Haisong Xia; Zhongzhi Zhang; |
| 304 | FLea: Addressing Data Scarcity and Label Skew in Federated Learning Via Privacy-preserving Feature Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, existing FL methods still face challenges when dealing with scarce and label-skewed data across devices, resulting in local model overfitting and drift, consequently hindering the performance of the global model. In response to these challenges, we propose a pioneering framework called FLea, incorporating the following key components: i) A global feature buffer that stores activation-target pairs shared from multiple clients to support local training. |
Tong Xia; Abhirup Ghosh; Xinchi Qiu; Cecilia Mascolo; |
| 305 | Predicting Cascading Failures with A Hyperparametric Diffusion Model Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we study cascading failures in power grids through the lens of information diffusion models. |
Bin Xiang; Bogdan Cautis; Xiaokui Xiao; Olga Mula; Dusit Niyato; Laks V.S. Lakshmanan; |
| 306 | Performative Debias with Fair-exposure Optimization Driven By Strategic Agents in Recommender Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite the abundance of research surrounding this issue, it still poses challenges and remains a hot topic in academic circles. Along this line, in this paper, we developed a re-ranking approach in dynamic settings with fair-exposure optimization driven by strategic agents. |
Zhichen Xiang; Hongke Zhao; Chuang Zhao; Ming He; Jianping Fan; |
| 307 | Motif-Consistent Counterfactuals with Adversarial Refinement for Graph-level Anomaly Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Most existing studies directly introduce perturbations (e.g., flipping edges) to generate counterfactual graphs, which are prone to alter the semantics of generated examples and make them off the data manifold, resulting in sub-optimal performance. To address these issues, we propose a novel approach, Motif-consistent Counterfactuals with Adversarial Refinement (MotifCAR), for graph-level anomaly detection. |
Chunjing Xiao; Shikang Pang; Wenxin Tai; Yanlong Huang; Goce Trajcevski; Fan Zhou; |
| 308 | ReFound: Crafting A Foundation Model for Urban Region Understanding Upon Language and Visual Foundations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Though there have been some attempts to empower the existing FMs with urban data, most of them focus on single-modality FMs without considering the multi-modality nature of urban region understanding tasks. To address this gap, we introduce ReFound – a novel framework for Re-training a Foundation model for urban region understanding, harnessing the strengths of both language and visual FMs. |
Congxi Xiao; Jingbo Zhou; Yixiong Xiao; Jizhou Huang; Hui Xiong; |
| 309 | How to Avoid Jumping to Conclusions: Measuring The Robustness of Outstanding Facts in Knowledge Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a methodology that inspects the robustness of OFs in KGs by perturbation analysis. |
Hanhua Xiao; Yuchen Li; Yanhao Wang; Panagiotis Karras; Kyriakos Mouratidis; Natalia Rozalia Avlona; |
| 310 | Make Your Home Safe: Time-aware Unsupervised User Behavior Anomaly Detection in Smart Homes Via Loss-guided Mask Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose SmartGuard, an autoencoder-based unsupervised user behavior anomaly detection framework. |
Jingyu Xiao; Zhiyao Xu; Qingsong Zou; Qing Li; Dan Zhao; Dong Fang; Ruoyu Li; Wenxin Tang; Kang Li; Xudong Zuo; Penghui Hu; Yong Jiang; Zixuan Weng; Michael R. Lyu; |
| 311 | Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes to design a joint graph data and architecture mechanism, which identifies important sub-architectures via the valuable graph data. |
Beini Xie; Heng Chang; Ziwei Zhang; Zeyang Zhang; Simin Wu; Xin Wang; Yuan Meng; Wenwu Zhu; |
| 312 | Preventing Strategic Behaviors in Collaborative Inference for Vertical Federated Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In order to elicit the true local embeddings for VFL system, we propose a distribution-based penalty mechanism to detect and penalize the strategic behaviors in collaborative inference. |
Yidan Xing; Zhenzhe Zheng; Fan Wu; |
| 313 | FRNet: Frequency-based Rotation Network for Long-term Time Series Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we dissect the original time series in time and frequency domains and empirically find that changes in periods are more easily captured and quantified in the frequency domain. |
Xinyu Zhang; Shanshan Feng; Jianghong Ma; Huiwei Lin; Xutao Li; Yunming Ye; Fan Li; Yew Soon Ong; |
| 314 | Temporal Prototype-Aware Learning for Active Voltage Control on Power Distribution Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose a novel temporal prototype-aware learning method, abbreviated as TPA, to learn time-adaptive AVC under short-term training trajectories. |
Feiyang Xu; Shunyu Liu; Yunpeng Qing; Yihe Zhou; Yuwen Wang; Mingli Song; |
| 315 | FlexCare: Leveraging Cross-Task Synergy for Flexible Multimodal Healthcare Prediction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Taking full account of the information disparities between different modalities and different tasks, we present a task-guided hierarchical multimodal fusion module that integrates the refined modality-level representations into an individual patient-level representation. |
Muhao Xu; Zhenfeng Zhu; Youru Li; Shuai Zheng; Yawei Zhao; Kunlun He; Yao Zhao; |
| 316 | PeFAD: A Parameter-Efficient Federated Framework for Time Series Anomaly Detection Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To bridge the gap between the decentralized time series data and the centralized anomaly detection algorithms, we propose a Parameter-efficient Federated Anomaly Detection framework named PeFAD with the increasing privacy concerns. |
Ronghui Xu; Hao Miao; Senzhang Wang; Philip S. Yu; Jianxin Wang; |
| 317 | ProtoMix: Augmenting Health Status Representation Learning Via Prototype-based Mixup Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This results in the generation of new samples that fail to preserve the subtype structure within EHR data, thereby limiting their practicality in health prediction tasks that generally require detailed patient phenotyping. Aiming at the above problems, we propose a Prototype-based Mixup method, dubbed ProtoMix, which combines prior knowledge of intrinsic data features from subtype centroids (i.e., prototypes) to guide the synthesis of new samples. |
Yongxin Xu; Xinke Jiang; Xu Chu; Yuzhen Xiao; Chaohe Zhang; Hongxin Ding; Junfeng Zhao; Yasha Wang; Bing Xie; |
| 318 | Improving Multi-modal Recommender Systems By Denoising and Aligning Multi-modal Content and User Feedback Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, previous studies overlook the challenges of (1)noisy multi-modal content, (2) noisy user feedback, and (3) aligning multi-modal content and user feedback. To tackle these challenges, we propose Denoising and Aligning Multi-modal Recommender System (DA-MRS). |
Guipeng Xv; Xinyu Li; Ruobing Xie; Chen Lin; Chong Liu; Feng Xia; Zhanhui Kang; Leyu Lin; |
| 319 | Extreme Meta-Classification for Large-Scale Zero-Shot Retrieval Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We develop accurate and efficient solutions for large-scale retrieval tasks where novel (zero-shot) items can arrive continuously at a rapid pace. |
Sachin Yadav; Deepak Saini; Anirudh Buvanesh; Bhawna Paliwal; Kunal Dahiya; Siddarth Asokan; Yashoteja Prabhu; Jian Jiao; Manik Varma; |
| 320 | FedRoLA: Robust Federated Learning Against Model Poisoning Via Layer-based Aggregation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Exacerbating these limitations is the fact that most existing defenses also fail to account for the distinctive contributions of Deep Neural Network (DNN) layers in detecting malicious activity, leading to the unnecessary rejection of benign updates. To bridge these gaps, we introduce FedRoLa, a cutting-edge similarity-based defense method optimized for FL. |
Gang Yan; Hao Wang; Xu Yuan; Jian Li; |
| 321 | Team Up GBDTs and DNNs: Advancing Efficient and Effective Tabular Prediction with Tree-hybrid MLPs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To address this model selection dilemma, this paper proposes a new framework that amalgamates the advantages of both GBDTs and DNNs, resulting in a DNN algorithm that is as efficient as GBDTs and is competitively effective regardless of dataset preferences for GBDTs or DNNs. |
Jiahuan Yan; Jintai Chen; Qianxing Wang; Danny Z. Chen; Jian Wu; |
| 322 | Efficient Mixture of Experts Based on Large Language Models for Low-Resource Data Preprocessing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present MELD (Mixture of Experts on Large Language Models for Data Preprocessing), a universal solver for low-resource DP. |
Mengyi Yan; Yaoshu Wang; Kehan Pang; Min Xie; Jianxin Li; |
| 323 | An Efficient Subgraph GNN with Provable Substructure Counting Power Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we tackle a critical question: Is it possible for GNNs to count substructures both efficiently and provably? |
Zuoyu Yan; Junru Zhou; Liangcai Gao; Zhi Tang; Muhan Zhang; |
| 324 | Revisiting Reciprocal Recommender Systems: Metrics, Formulation, and Method Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, the majority of existing methods in the literature still reuse conventional ranking metrics to separately assess the performance on each side of the recommendation process. These methods overlook the fact that the ranking outcomes of both sides collectively influence the effectiveness of the RRS, neglecting the necessity of a more holistic evaluation and a capable systemic solution.In this paper, we systemically revisit the task of reciprocal recommendation, by introducing the new metrics, formulation, and method. |
Chen Yang; Sunhao Dai; Yupeng Hou; Wayne Xin Zhao; Jun Xu; Yang Song; Hengshu Zhu; |
| 325 | Noisy Label Removal for Partial Multi-Label Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Specifically, we propose a constrained regression model to learn a PML classifier and select the noisy labels. |
Fuchao Yang; Yuheng Jia; Hui Liu; Yongqiang Dong; Junhui Hou; |
| 326 | Towards Test Time Adaptation Via Calibrated Entropy Minimization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In response, we introduce a novel confidence-calibration loss function called Calibrated Entropy Test-Time Adaptation (CETA), which considers the model’s largest logit and the next-highest-ranked one, aiming to strike a balance between overconfidence and underconfidence. |
Hao Yang; Min Wang; Jinshen Jiang; Yun Zhou; |
| 327 | Balanced Confidence Calibration for Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our investigation in this work reveals that most existing GNN calibration methods predominantly focus on the highest logit, thereby neglecting the entire spectrum of prediction probabilities. To alleviate this limitation, we introduce a novel framework called Balanced Calibrated Graph Neural Network (BCGNN), specifically designed to establish a balanced calibration between over-confidence and under-confidence in GNNs’ prediction. |
Hao Yang; Min Wang; Qi Wang; Mingrui Lao; Yun Zhou; |
| 328 | Efficient Decision Rule List Learning Via Unified Sequence Submodular Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we focus on learning a decision rule list for binary and multi-class classification. |
Linxiao Yang; Jingbang Yang; Liang Sun; |
| 329 | Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Space Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This stems primarily from: (i) the absence of well-defined modules in hyperbolic space, including linear transformation layers, LayerNorm layers, activation functions, dropout operations, etc. (ii) the quadratic time complexity of the existing hyperbolic self-attention module w.r.t the number of input tokens, which hinders its scalability. To address these challenges, we propose, Hypformer, a novel hyperbolic Transformer based on the Lorentz model of hyperbolic geometry. |
Menglin Yang; Harshit Verma; Delvin Ce Zhang; Jiahong Liu; Irwin King; Rex Ying; |
| 330 | Effective Clustering on Large Attributed Bipartite Graphs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, the majority of existing solutions towards k-ABGC either overlook attribute information or fail to capture bipartite graph structures accurately, engendering severely compromised result quality. The severity of these issues is accentuated in real ABGs, which often encompass millions of nodes and a sheer volume of attribute data, rendering effective k-ABGC over such graphs highly challenging.In this paper, we propose TPO, an effective and efficient approach to k-ABGC that achieves superb clustering performance on multiple real datasets. |
Renchi Yang; Yidu Wu; Xiaoyang Lin; Qichen Wang; Tsz Nam Chan; Jieming Shi; |
| 331 | Practical Single Domain Generalization Via Training-time and Test-time Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a Practical Single Domain Generalization (PSDG) method, which first leverages the knowledge in a source domain to establish a model with good generalization ability in the training phase, and subsequently updates the model to adapt to target domain data using knowledge in the unlabeled target domain during the testing phase. |
Shuai Yang; Zhen Zhang; Lichuan Gu; |
| 332 | Conversational Dueling Bandits in Generalized Linear Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Moreover, current contextual bandit methods mainly work under linear reward assumptions, ignoring practical non-linear reward structures in generalized linear models. Therefore, in this paper, we introduce relative feedback-based conversations into conversational recommendation systems through the integration of dueling bandits in generalized linear models (GLM) and propose a novel conversational dueling bandit algorithm called ConDuel. |
Shuhua Yang; Hui Yuan; Xiaoying Zhang; Mengdi Wang; Hong Zhang; Huazheng Wang; |
| 333 | ReCDA: Concept Drift Adaptation with Representation Enhancement for Network Intrusion Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose ReCDA, a Concept Drift Adaptation method with Representation enhancement, which consists of a self-supervised representation enhancement stage and a weakly-supervised classifier tuning stage. |
Shuo Yang; Xinran Zheng; Jinze Li; Jinfeng Xu; Xingjun Wang; Edith C. H. Ngai; |
| 334 | Your Neighbor Matters: Towards Fair Decisions Under Networked Interference Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Unfortunately, conventional fairness approaches often assume independent individuals, overlooking the impact of one person’s sensitive attribute on others’ decisions. To fill this gap, we introduce Interference-aware Fairness (IAF) by defining two forms of discrimination as Self-Fairness (SF) and Peer-Fairness (PF), leveraging advances in interference analysis within causal inference. |
Wenjing Yang; Haotian Wang; Haoxuan Li; Hao Zou; Ruochun Jin; Kun Kuang; Peng Cui; |
| 335 | SEBot: Structural Entropy Guided Multi-View Contrastive Learning for Social Bot Detection Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose SEBot, a novel multi-view graph-based contrastive learning-enabled social bot detector. |
Yingguang Yang; Qi Wu; Buyun He; Hao Peng; Renyu Yang; Zhifeng Hao; Yong Liao; |
| 336 | Graph Bottlenecked Social Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we focus on learning the denoised social structure to facilitate recommendation tasks from an information bottleneck perspective. |
Yonghui Yang; Le Wu; Zihan Wang; Zhuangzhuang He; Richang Hong; Meng Wang; |
| 337 | Rethinking Order Dispatching in Online Ride-Hailing Platforms Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper models such impact within a cooperative Markov game, which involves each value’s impact over the platform’s revenue with the goal to find the optimal region values for revenue maximization. To solve this game, our work proposes a novelgoal-reaching collaboration (GRC) algorithm that realizes credit assignment from a novel goal-reaching perspective, addressing the difficulty for accurate credit assignment with large-scale agents of previous methods and resolving the conflict between credit assignment and offline reinforcement learning. |
Zhaoxing Yang; Haiming Jin; Guiyun Fan; Min Lu; Yiran Liu; Xinlang Yue; Hao Pan; Zhe Xu; Guobin Wu; Qun Li; Xiaotong Wang; Jiecheng Guo; |
| 338 | User Welfare Optimization in Recommender Systems with Competing Content Creators Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an algorithmic solution for the platform, which dynamically computes a sequence of weights for each user based on their satisfaction of the recommended content. |
Fan Yao; Yiming Liao; Mingzhe Wu; Chuanhao Li; Yan Zhu; James Yang; Jingzhou Liu; Qifan Wang; Haifeng Xu; Hongning Wang; |
| 339 | AdaRD: An Adaptive Response Denoising Framework for Robust Learner Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a general framework, Adaptive Response Denoising (AdaRD), designed to salvage CDMs from the influence of noisy learner-exercise responses. |
Fangzhou Yao; Qi Liu; Linan Yue; Weibo Gao; Jiatong Li; Xin Li; Yuanjing He; |
| 340 | Approximate Matrix Multiplication Over Sliding Windows Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In addition, many practical scenarios require to process time-sensitive data and aim to compute matrix multiplication for most recent columns of the data matrices rather than the entire matrices, which motivated us to study efficient AMM algorithms over sliding windows. In this paper, we present two novel deterministic algorithms for this problem and provide corresponding error guarantees. |
Ziqi Yao; Lianzhi Li; Mingsong Chen; Xian Wei; Cheng Chen; |
| 341 | Efficient and Effective Anchored Densest Subgraph Search: A Convex-programming Based Approach Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This allows us to transition into a dual problem, tapping into the efficiency and effectiveness of convex programming-based iterative algorithm. To solve this redefined problem, we propose two algorithms: FDP, an iterative method that swiftly attains near-optimal solutions, and FDPE, an exact approach that ensures full convergence. |
Xiaowei Ye; Rong-Hua Li; Lei Liang; Zhizhen Liu; Longlong Lin; Guoren Wang; |
| 342 | RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we investigate the potential of addressing spatial-temporal forecasting problems using general time series forecasting models, i.e., models that do not leverage the spatial relationships among the nodes. |
Chin-Chia Michael Yeh; Yujie Fan; Xin Dai; Uday Singh Saini; Vivian Lai; Prince Osei Aboagye; Junpeng Wang; Huiyuan Chen; Yan Zheng; Zhongfang Zhuang; Liang Wang; Wei Zhang; |
| 343 | Embedding Two-View Knowledge Graphs with Class Inheritance and Structural Similarity Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite the consideration to bridge the gap among two-view KG representations, existing methods ignore the existence of structural similarity between two-view KGs. To address these issues, we propose a novel two-view KG embedding model, CISS, considering Class Inheritance and Structural Similarity between two-view KGs. |
Kyuhwan Yeom; Hyeongjun Yang; Gayeon Park; Myeongheon Jeon; Yunjeong Ko; Byungkook Oh; Kyong-Ho Lee; |
| 344 | Using Self-supervised Learning Can Improve Model Fairness Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We introduce a fairness assessment framework for SSL, comprising five stages: defining dataset requirements, pre-training, fine-tuning with gradual unfreezing, assessing representation similarity conditioned on demographics, and establishing domain-specific evaluation processes. |
Sofia Yfantidou; Dimitris Spathis; Marios Constantinides; Athena Vakali; Daniele Quercia; Fahim Kawsar; |
| 345 | Dataset Regeneration for Sequential Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Driven by the potential of data-centric AI, we propose a novel data-centric paradigm for developing an ideal training dataset using a model-agnostic dataset regeneration framework called DR4SR. |
Mingjia Yin; Hao Wang; Wei Guo; Yong Liu; Suojuan Zhang; Sirui Zhao; Defu Lian; Enhong Chen; |
| 346 | Unsupervised Generative Feature Transformation Via Graph Contrastive Pre-training and Multi-objective Fine-tuning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For unsupervised feature set utility measurement, we propose a feature value consistency preservation perspective and develop a mean discounted cumulative gain like unsupervised metric to evaluate feature set utility. |
Wangyang Ying; Dongjie Wang; Xuanming Hu; Yuanchun Zhou; Charu C. Aggarwal; Yanjie Fu; |
| 347 | Top-Down Bayesian Posterior Sampling for Sum-Product Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study aimed to develop a Bayesian learning approach that can be efficiently implemented on large-scale SPNs. |
Soma Yokoi; Issei Sato; |
| 348 | GinAR: An End-To-End Multivariate Time Series Forecasting Model Suitable for Variable Missing Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To address the problem, in this paper, we propose a novel Graph Interpolation Attention Recursive Network (named GinAR) to precisely model the spatial-temporal dependencies over the limited collected data for forecasting. |
Chengqing Yu; Fei Wang; Zezhi Shao; Tangwen Qian; Zhao Zhang; Wei Wei; Yongjun Xu; |
| 349 | Self-consistent Deep Geometric Learning for Heterogeneous Multi-source Spatial Point Data Prediction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Key challenges include evaluating the quality of different data sources and modeling spatial relationships among them effectively. Addressing these issues, we introduce an innovative multi-source spatial point data prediction framework that adeptly aligns information from varied sources without relying on ground truth labels. |
Dazhou Yu; Xiaoyun Gong; Yun Li; Meikang Qiu; Liang Zhao; |
| 350 | PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: While recent years have seen considerable advancements in this field, much of the focus has been on single polygons, overlooking the intricate inner- and inter-polygonal relationships inherent in multipolygons. To address this gap, our study introduces a comprehensive framework specifically designed for learning representations of polygonal geometries, particularly multipolygons. |
Dazhou Yu; Yuntong Hu; Yun Li; Liang Zhao; |
| 351 | Personalized Federated Continual Learning Via Multi-Granularity Prompt Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we propose a novel concept called multi-granularity prompt, i.e., coarse-grained global prompt acquired through the common model learning process, and fine-grained local prompt used to personalize the generalized representation. |
Hao Yu; Xin Yang; Xin Gao; Yan Kang; Hao Wang; Junbo Zhang; Tianrui Li; |
| 352 | BoKA: Bayesian Optimization Based Knowledge Amalgamation for Multi-unknown-domain Text Classification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To learn an accurate student model, the classical KA method resorts to manual selections, a process both tedious and inefficient. Our study pioneers the automation of this combination selection process for KA in the fundamental text classification task, an area previously unexplored.In this paper, we introduce BoKA�: an automatic knowledge amalgamation framework for identifying a combination that can learn a superior student model without human labor. |
Linzhu Yu; Huan Li; Ke Chen; Lidan Shou; |
| 353 | RIGL: A Unified Reciprocal Approach for Tracing The Independent and Group Learning Processes Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, in this paper, we propose RIGL, a unified Reciprocal model to trace knowledge states at both the individual and group levels, drawing from the Independent and Group Learning processes. |
Xiaoshan Yu; Chuan Qin; Dazhong Shen; Shangshang Yang; Haiping Ma; Hengshu Zhu; Xingyi Zhang; |
| 354 | Unveiling Privacy Vulnerabilities: Investigating The Role of Structure in Graph Data Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Based on this insight, we develop a novel graph private attribute inference attack, which acts as a pivotal tool for evaluating the potential for privacy leakage through network structures under worst-case scenarios. To protect users’ private data from such vulnerabilities, we propose a graph data publishing method incorporating a learnable graph sampling technique, effectively transforming the original graph into a privacy-preserving version. |
Hanyang Yuan; Jiarong Xu; Cong Wang; Ziqi Yang; Chunping Wang; Keting Yin; Yang Yang; |
| 355 | DipDNN: Preserving Inverse Consistency and Approximation Efficiency for Invertible Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Based on the observation, we propose decomposed-invertible-pathway DNNs (DipDNN). |
Jingyi Yuan; Yang Weng; Erik Blasch; |
| 356 | Graph Cross Supervised Learning Via Generalized Knowledge Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we formulate a new problem, Graph Cross-Supervised Learning, or Graph Weak-Shot Learning, that describes the challenges of modeling new nodes with novel classes and potential label noises. To solve this problem, we propose Lipshitz-regularized Mixture-of-Experts similarity network (LIME), a novel framework to encode new nodes and handle label noises. |
Xiangchi Yuan; Yijun Tian; Chunhui Zhang; Yanfang Ye; Nitesh V. Chawla; Chuxu Zhang; |
| 357 | UniST: A Prompt-Empowered Universal Model for Urban Spatio-Temporal Prediction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we introduce UniST, a universal model designed for general urban spatio-temporal prediction across a wide range of scenarios. |
Yuan Yuan; Jingtao Ding; Jie Feng; Depeng Jin; Yong Li; |
| 358 | Effective Generation of Feasible Solutions for Integer Programming Via Guided Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose a novel framework that generates complete feasible solutions end-to-end. |
Hao Zeng; Jiaqi Wang; Avirup Das; Junying He; Kunpeng Han; Haoyuan Hu; Mingfei Sun; |
| 359 | Conditional Logical Message Passing Transformer for Complex Query Answering Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose Conditional Logical Message Passing Transformer (CLMPT), which considers the difference between constants and variables in the case of using pre-trained neural link predictors and performs message passing conditionally on the node type. |
Chongzhi Zhang; Zhiping Peng; Junhao Zheng; Qianli Ma; |
| 360 | GPFedRec: Graph-Guided Personalization for Federated Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Inspired by a simple motivation, similar users share a similar vision (embeddings) to the same item set, this paper proposes a novel Graph-guided Personalization for Federated Recommendation (GPFedRec). |
Chunxu Zhang; Guodong Long; Tianyi Zhou; Zijian Zhang; Peng Yan; Bo Yang; |
| 361 | Path-Specific Causal Reasoning for Fairness-aware Cognitive Diagnosis Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In response, we argue that sensitive attributes of students can also provide useful information, and only the shortcuts directly related to the sensitive information should be eliminated from the diagnosis process. Thus, we employ causal reasoning and design a novel Path-Specific Causal Reasoning Framework (PSCRF) to achieve this goal. |
Dacao Zhang; Kun Zhang; Le Wu; Mi Tian; Richang Hong; Meng Wang; |
| 362 | Brant-X: A Unified Physiological Signal Alignment Framework Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Nevertheless, achieving this goal is still constrained by several challenges: the scarcity of simultaneously collected physiological data, the differences in correlations between various signals, and the correlation differences between various tasks. To address these issues, we propose a unified physiological signal alignment framework, Brant-X, to model the correlation between EEG and other signals. |
Daoze Zhang; Zhizhang Yuan; Junru Chen; Kerui Chen; Yang Yang; |
| 363 | Item-Difficulty-Aware Learning Path Recommendation: From A Real Walking Perspective Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To conquer the above limitations, we propose a novel method named Difficulty-constrained Learning Path Recommendation (DLPR), which is aware of item difficulty. Specifically, we first explicitly categorize items into learning items and practice items, then construct a hierarchical graph to model and leverage item difficulty adequately. |
Haotian Zhang; Shuanghong Shen; Bihan Xu; Zhenya Huang; Jinze Wu; Jing Sha; Shijin Wang; |
| 364 | Subspace Selection Based Prompt Tuning with Nonconvex Nonsmooth Black-Box Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce a novel framework for black-box prompt tuning with a subspace learning and selection strategy, leveraging derivative-free optimization algorithms. |
Haozhen Zhang; Hualin Zhang; Bin Gu; Yi Chang; |
| 365 | Enabling Collaborative Test-Time Adaptation in Dynamic Environment Via Federated Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, implementing FL in TTA presents many challenges, especially in establishing inter-client collaboration in dynamic environment, where the test data distribution on different clients changes over time in different manners. To tackle these challenges, we propose a server-side Temporal-Spatial Aggregation (TSA) method. |
Jiayuan Zhang; Xuefeng Liu; Yukang Zhang; Guogang Zhu; Jianwei Niu; Shaojie Tang; |
| 366 | Natural Language Explainable Recommendation with Robustness Enhancement Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Different from traditional classification problems, improving the robustness of natural languages has two unique characteristics: (1) Different token importances, that is, different tokens play various roles in representing the complete sentence, and the robustness requirements for predicting them should also be different. (2) Continuous token semantics, that is, the similarity of the output should be judged based on semantics, and the sequences without any token-level overlap may also be highly similar. Based on these characteristics, we formulate and solve a novel problem in the recommendation domain, that is, robust natural language explainable recommendation. |
Jingsen Zhang; Jiakai Tang; Xu Chen; Wenhui Yu; Lantao Hu; Peng Jiang; Han Li; |
| 367 | Diverse Intra- and Inter-Domain Activity Style Fusion for Cross-Person Generalization in Activity Recognition Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Existing domain generalization (DG) methods for cross-person generalization tasks often face challenges in capturing intra- and inter-domain style diversity, resulting in domain gaps with the target domain. In this study, we explore a novel perspective to tackle this problem, a process conceptualized as domain padding. |
Junru Zhang; Lang Feng; Zhidan Liu; Yuhan Wu; Yang He; Yabo Dong; Duanqing Xu; |
| 368 | Heuristic Learning with Graph Neural Networks: A Unified Framework for Link Prediction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Drawing insights from the fact that both local and global heuristics can be represented by adjacency matrix multiplications, we propose a unified matrix formulation to accommodate and generalize various heuristics. |
Juzheng Zhang; Lanning Wei; Zhen Xu; Quanming Yao; |
| 369 | Optimized Cost Per Click in Online Advertising: A Theoretical Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To fill the gap, this paper builds an economic model that compares OCPC with CPC and CPA theoretically, which incorporates out-site scenarios and outside options as two key factors. |
Kaichen Zhang; Zixuan Yuan; Hui Xiong; |
| 370 | Asynchronous Vertical Federated Learning for Kernelized AUC Maximization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the double imbalance issue, we propose Asynchronous Vertical Federated Kernelized AUC Maximization (AVFKAM). |
Ke Zhang; Ganyu Wang; Han Li; Yulong Wang; Hong Chen; Bin Gu; |
| 371 | Multivariate Log-based Anomaly Detection for Distributed Database Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our findings reveal that relying solely on logs from a single node is insufficient for accurate anomaly detection on distributed database. Leveraging these insights, we propose MultiLog, an innovative multivariate log-based anomaly detection approach tailored for distributed databases. |
Lingzhe Zhang; Tong Jia; Mengxi Jia; Ying Li; Yong Yang; Zhonghai Wu; |
| 372 | Logical Reasoning with Relation Network for Inductive Knowledge Graph Completion Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose a novel iNfOmax RelAtion Network, namely NORAN, for inductive KG completion. |
Qinggang Zhang; Keyu Duan; Junnan Dong; Pai Zheng; Xiao Huang; |
| 373 | Knowledge Distillation with Perturbed Loss: From A Vanilla Teacher to A Proxy Teacher Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output distribution with the teacher’s output distribution. In this work, we argue that such a learning objective is sub-optimal because there exists a discrepancy between the teacher’s output distribution and the ground truth label distribution. |
Rongzhi Zhang; Jiaming Shen; Tianqi Liu; Jialu Liu; Michael Bendersky; Marc Najork; Chao Zhang; |
| 374 | Towards Adaptive Neighborhood for Advancing Temporal Interaction Graph Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we aim to enhance existing TGNs by introducing anadaptive neighborhood encoding mechanism. |
Siwei Zhang; Xi Chen; Yun Xiong; Xixi Wu; Yao Zhang; Yongrui Fu; Yinglong Zhao; Jiawei Zhang; |
| 375 | Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose an Asynchronous Spatio-tEmporal graph convolutional nEtwoRk (ASeer) tailored for irregular traffic time series forecasting. |
Weijia Zhang; Le Zhang; Jindong Han; Hao Liu; Yanjie Fu; Jingbo Zhou; Yu Mei; Hui Xiong; |
| 376 | A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While advanced AI techniques like deep learning and reinforcement learning are extensively utilized in finance, their application in financial trading tasks often faces challenges due to inadequate handling of multimodal data and limited generalizability across various tasks. To address these challenges, we present FinAgent, a multimodal foundational agent with tool augmentation for financial trading. |
Wentao Zhang; Lingxuan Zhao; Haochong Xia; Shuo Sun; Jiaze Sun; Molei Qin; Xinyi Li; Yuqing Zhao; Yilei Zhao; Xinyu Cai; Longtao Zheng; Xinrun Wang; Bo An; |
| 377 | Topology-aware Embedding Memory for Continual Learning on Expanding Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we systematically analyze the key challenges in the memory explosion problem, and present a general framework,i.e., Parameter Decoupled Graph Neural Networks (PDGNNs) with Topology-aware Embedding Memory (TEM), to tackle this issue. |
Xikun Zhang; Dongjin Song; Yixin Chen; Dacheng Tao; |
| 378 | Geometric View of Soft Decorrelation in Self-Supervised Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While the decorrelation term is designed to address the issue of dimensional collapse, we find that it fails to achieve this goal theoretically and experimentally. Based on such a finding, we extend the soft decorrelation regularization to minimize the distance between the covariance matrix and an identity matrix. |
Yifei Zhang; Hao Zhu; Zixing Song; Yankai Chen; Xinyu Fu; Ziqiao Meng; Piotr Koniusz; Irwin King; |
| 379 | LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs? Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we bridge the gap via proposing to evaluate LLMs’ spatial-temporal understanding abilities on dynamic graphs, to the best of our knowledge, for the first time. |
Zeyang Zhang; Xin Wang; Ziwei Zhang; Haoyang Li; Yijian Qin; Wenwu Zhu; |
| 380 | Joint Auction in The Online Advertising Market Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, the currently used advertising mode cannot satisfy the demand of both stores and brand suppliers simultaneously. To address this, we innovatively propose a joint advertising model termed ”Joint Auction”, allowing brand suppliers and stores to collaboratively bid for advertising slots, catering to both their needs. |
Zhen Zhang; Weian Li; Yahui Lei; Bingzhe Wang; Zhicheng Zhang; Qi Qi; Qiang Liu; Xingxing Wang; |
| 381 | Representation Learning of Geometric Trees Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This inherent hierarchical structure plays a crucial role in domains such as neuron morphology and river geomorphology, but traditional graph representation methods often overlook these specific characteristics of tree structures. To address this, we introduce a new representation learning framework tailored for geometric trees. |
Zheng Zhang; Allen Zhang; Ruth Nelson; Giorgio Ascoli; Liang Zhao; |
| 382 | Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Hence, these injected triggers can be easily detected and pruned with widely used outlier detection methods in real-world applications. Therefore, in this paper, we study a novel problem of unnoticeable graph backdoor attacks with in-distribution (ID) triggers. |
Zhiwei Zhang; Minhua Lin; Enyan Dai; Suhang Wang; |
| 383 | Long-Term Vessel Trajectory Imputation with Physics-Guided Diffusion Probabilistic Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Existing imputation approaches are often constrained by vehicle-based low-sampling trajectories, hindering their ability to address unique characteristics of maritime transportation systems and long-term missing scenarios. To tackle these challenges, we propose a novel generative framework for long-term vessel trajectory imputation. |
Zhiwen Zhang; Zipei Fan; Zewu Lv; Xuan Song; Ryosuke Shibasaki; |
| 384 | Learning Flexible Time-windowed Granger Causality Integrating Heterogeneous Interventional Time Series Data Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Our work presents a theoretically-grounded method that infers Granger causal structure and identifies unknown targets by leveraging heterogeneous interventional time series data. |
Ziyi Zhang; Shaogang Ren; Xiaoning Qian; Nick Duffield; |
| 385 | Algorithmic Fairness Generalization Under Covariate and Dependence Shifts Simultaneously Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we introduce a simple but effective approach that aims to learn a fair and invariant classifier by simultaneously addressing both covariate and dependence shifts across domains. |
Chen Zhao; Kai Jiang; Xintao Wu; Haoliang Wang; Latifur Khan; Christan Grant; Feng Chen; |
| 386 | VertiMRF: Differentially Private Vertical Federated Data Synthesis Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose a novel algorithm called VertiMRF, designed explicitly for generating synthetic data in the vertical setting and providing differential privacy protection for all information shared from data parties. |
Fangyuan Zhao; Zitao Li; Xuebin Ren; Bolin Ding; Shusen Yang; Yaliang Li; |
| 387 | All in One and One for All: A Simple Yet Effective Method Towards Cross-domain Graph Pretraining Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This issue is particularly important in few-shot learning scenarios, where the paucity of training data necessitates the incorporation of external knowledge sources. In response to this challenge, we propose a novel approach called Graph COordinators for PrEtraining (GCOPE), that harnesses the underlying commonalities across diverse graph datasets to enhance few-shot learning. |
Haihong Zhao; Aochuan Chen; Xiangguo Sun; Hong Cheng; Jia Li; |
| 388 | Counteracting Duration Bias in Video Recommendation Via Counterfactual Watch Time Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Although effective to some extent, we found that these approaches regard completely played records (i.e., a user watches the entire video) as equally high interest, which deviates from what we observed on real datasets: users have varied explicit feedback proportion when completely playing videos. In this paper, we introduce the counterfactual watch time (CWT), the potential watch time a user would spend on the video if its duration is sufficiently long. |
Haiyuan Zhao; Guohao Cai; Jieming Zhu; Zhenhua Dong; Jun Xu; Ji-Rong Wen; |
| 389 | Pre-Training and Prompting for Few-Shot Node Classification on Text-Attributed Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose P2TAG, a framework designed for few-shot node classification on TAGs with graph pre-training and prompting. |
Huanjing Zhao; Beining Yang; Yukuo Cen; Junyu Ren; Chenhui Zhang; Yuxiao Dong; Evgeny Kharlamov; Shu Zhao; Jie Tang; |
| 390 | Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we tackle a new problem ofmulti-source unsupervised domain adaptation (MSUDA) for graphs, where models trained on annotated source domains need to be transferred to the unsupervised target graph for node classification. |
Tianxiang Zhao; Dongsheng Luo; Xiang Zhang; Suhang Wang; |
| 391 | Conformalized Link Prediction on Graph Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This work makes the first attempt to introduce a distribution-free and model-agnostic uncertainty quantification approach to construct a predictive interval with a statistical guarantee for GNN-based link prediction. |
Tianyi Zhao; Jian Kang; Lu Cheng; |
| 392 | GeoMix: Towards Geometry-Aware Data Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose Geometric Mixup (GeoMix), a simple and interpretable Mixup approach leveraging in-place graph editing. |
Wentao Zhao; Qitian Wu; Chenxiao Yang; Junchi Yan; |
| 393 | Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce MODA – a Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing approach. |
Xinbo Zhao; Yingxue Zhang; Xin Zhang; Yu Yang; Yiqun Xie; Yanhua Li; Jun Luo; |
| 394 | Spuriousness-Aware Meta-Learning for Learning Robust Classifiers Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose a novel learning framework based on meta-learning, termed SPUME — SPUriousness-aware MEta-learning, to train an image classifier to be robust to spurious correlations. |
Guangtao Zheng; Wenqian Ye; Aidong Zhang; |
| 395 | SiGeo: Sub-One-Shot NAS Via Geometry of Loss Landscape Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Within this framework, we present SiGeo, a proxy founded on a novel theoretical framework that connects the supernet warm-up with the efficacy of the proxy. |
Hua Zheng; Kuang-Hung Liu; Igor Fedorov; Xin Zhang; Wen-Yen Chen; Wei Wen; |
| 396 | Relaxing Continuous Constraints of Equivariant Graph Neural Networks for Broad Physical Dynamics Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a general Discrete Equivariant Graph Neural Network (DEGNN) that guarantees equivariance to a given discrete point group. |
Zinan Zheng; Yang Liu; Jia Li; Jianhua Yao; Yu Rong; |
| 397 | LogParser-LLM: Advancing Efficient Log Parsing with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: With their expansive knowledge and contextual prowess, LLMs have been transformative across diverse applications. Building on this, we introduce LogParser-LLM, a novel log parser integrated with LLM capabilities. |
Aoxiao Zhong; Dengyao Mo; Guiyang Liu; Jinbu Liu; Qingda Lu; Qi Zhou; Jiesheng Wu; Quanzheng Li; Qingsong Wen; |
| 398 | Bridging and Compressing Feature and Semantic Spaces for Robust Graph Neural Networks: An Information Theory Perspective Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, existing studies commonly ignore the distribution difference between feature and semantic spaces in graphs, causing inferior model generalization. To address these challenges, we propose DIB-RGCN, a novel robust GCN framework, to explore the optimal graph representation with the guidance of the well-designed dual information bottleneck principle. |
Luying Zhong; Renjie Lin; Jiayin Li; Shiping Wang; Zheyi Chen; |
| 399 | BitLINK: Temporal Linkage of Address Clusters in Bitcoin Blockchain Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Links (i.e., trust relationships) between these disjoint address clusters can be established when one cluster is abandoned, and a new one is formed shortly thereafter. To link the clusters across time, we have developed a deep neural network model that exploits these synchronous actions derived from unlabeled data in a self-supervised manner. |
Sheng Zhong; Abdullah Mueen; |
| 400 | Efficient and Effective Implicit Dynamic Graph Neural Network Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We then demonstrate that the standard iterative algorithm often used to train implicit models is computationally expensive in our dynamic setting as it involves computing gradients, which themselves have to be estimated in an iterative manner. To overcome this, we pose an equivalent bilevel optimization problem and propose an efficient single-loop training algorithm that avoids iterative computation by maintaining moving averages of key components of the gradients. |
Yongjian Zhong; Hieu Vu; Tianbao Yang; Bijaya Adhikari; |
| 401 | Synthesizing Multimodal Electronic Health Records Via Predictive Diffusion Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, their ability to learn visit representations is limited due to simple linear mapping functions, thus compromising generation quality. To address these limitations, we propose a novel EHR data generation model called EHRPD. |
Yuan Zhong; Xiaochen Wang; Jiaqi Wang; Xiaokun Zhang; Yaqing Wang; Mengdi Huai; Cao Xiao; Fenglong Ma; |
| 402 | CURLS: Causal Rule Learning for Subgroups with Significant Treatment Effect Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose CURLS, a novel rule learning method leveraging HTE, which can effectively describe subgroups with significant treatment effects. |
Jiehui Zhou; Linxiao Yang; Xingyu Liu; Xinyue Gu; Liang Sun; Wei Chen; |
| 403 | Neural Collapse Anchored Prompt Tuning for Generalizable Vision-Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To improve the representations, we propose Neural-collapse-anchored Prompt Tuning (NPT), a novel method that learns prompts with text and image representations that satisfy the same simplex Equiangular Tight Frame (ETF). |
Didi Zhu; Zexi Li; Min Zhang; Junkun Yuan; Jiashuo Liu; Kun Kuang; Chao Wu; |
| 404 | Dynamic Hotel Pricing at Online Travel Platforms: A Popularity and Competitiveness Aware Demand Learning Approach Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a dynamic pricing approach with popularity and competitiveness-aware demand learning. |
Fanwei Zhu; Wendong Xiao; Yao Yu; Zemin Liu; Zulong Chen; Weibin Cai; |
| 405 | Propagation Structure-Aware Graph Transformer for Robust and Interpretable Fake News Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Furthermore, they inadequately capture intricate patterns inherent in long-sequence dependencies of news propagation due to their use of shallow GNNs aimed at avoiding the over-smoothing issue, consequently diminishing their overall accuracy. In this paper, we address these issues by proposing the Propagation Structure-aware Graph Transformer (PSGT). |
Junyou Zhu; Chao Gao; Ze Yin; Xianghua Li; Juergen Kurths; |
| 406 | Distributed Thresholded Counting with Limited Interaction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we focus on the Distributed Thresholded Counting problem in the coordinator model. |
Xiaoyi Zhu; Yuxiang Tian; Zengfeng Huang; |
| 407 | ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, existing trajectory generation methods are still in their infancy due to the inherent diversity and unpredictability of human activities, grappling with issues such as fidelity, flexibility, and generalizability. To overcome these obstacles, we propose ControlTraj, a Controllable Trajectory generation framework with the topology-constrained diffusion model. |
Yuanshao Zhu; James Jianqiao Yu; Xiangyu Zhao; Qidong Liu; Yongchao Ye; Wei Chen; Zijian Zhang; Xuetao Wei; Yuxuan Liang; |
| 408 | One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Accordingly, we propose a graph fairness framework based on invariant learning, namely FairINV, which enables the training of fair GNNs to accommodate various sensitive attributes within a single training session. |
Yuchang Zhu; Jintang Li; Yatao Bian; Zibin Zheng; Liang Chen; |
| 409 | Topology-monitorable Contrastive Learning on Dynamic Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Directly applying these models to dynamic graphs brings in severe efficiency issues in repetitively updating the learned embeddings. To address this challenge, we propose IDOL, a novel contrastive learning framework for dynamic graph representation learning. |
Zulun Zhu; Kai Wang; Haoyu Liu; Jintang Li; Siqiang Luo; |
| 410 | MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, existing RL methods for HFT still have some defects: 1) standard RL-based trading agents suffer from the overfitting issue, preventing them from making effective policy adjustments based on financial context; 2) due to the rapid changes in market conditions, investment decisions made by an individual agent are usually one-sided and highly biased, which might lead to significant loss in extreme markets. To tackle these problems, we propose a novel Memory Augmented Context-aware Reinforcement learning method On HFT, a.k.a. MacroHFT, which consists of two training phases: 1) we first train multiple types of sub-agents with the market data decomposed according to various financial indicators, specifically market trend and volatility, where each agent owns a conditional adapter to adjust its trading policy according to market conditions; 2) then we train a hyper-agent to mix the decisions from these sub-agents and output a consistently profitable meta-policy to handle rapid market fluctuations, equipped with a memory mechanism to enhance the capability of decision-making |
Chuqiao Zong; Chaojie Wang; Molei Qin; Lei Feng; Xinrun Wang; Bo An; |
| 411 | Repeat-Aware Neighbor Sampling for Dynamic Graph Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Only considering the recent neighbors overlooks the phenomenon of repeat behavior and fails to accurately capture the temporal evolution of interactions. To fill this gap, this paper presents RepeatMixer, which considers evolving patterns of first and high-order repeat behavior in the neighbor sampling strategy and temporal information learning. |
Tao Zou; Yuhao Mao; Junchen Ye; Bowen Du; |
| 412 | Dynamic Pricing for Multi-Retailer Delivery Platforms with Additive Deep Learning and Evolutionary Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a novel scheme to scalable and practical price adjustment in the highly dynamic multi-retailer context. |
Ahmed Abdulaal; Ali Polat; Hari Narayan; Wenrong Zeng; Yimin Yi; |
| 413 | Television Discourse Decoded: Comprehensive Multimodal Analytics at Scale Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we tackle the complex task of analyzing televised debates, with a focus on a prime time news debate show from India. |
Anmol Agarwal; Pratyush Priyadarshi; Shiven Sinha; Shrey Gupta; Hitkul Jangra; Ponnurangam Kumaraguru; Kiran Garimella; |
| 414 | DDCDR: A Disentangle-based Distillation Framework for Cross-Domain Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel Disentangle-based Distillation Framework for Cross-Domain Recommendation (DDCDR), designed to operate at the representational level and rooted in the established teacher-student knowledge distillation paradigm. |
Zhicheng An; Zhexu Gu; Li Yu; Ke Tu; Zhengwei Wu; Binbin Hu; Zhiqiang Zhang; Lihong Gu; Jinjie Gu; |
| 415 | GradCraft: Elevating Multi-task Recommendations Through Holistic Gradient Crafting Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, existing multi-task learning methods in recommendations overlook the specific characteristics of recommendation scenarios, falling short in achieving proper gradient balance. To address this challenge, we set the target of multi-task learning as attaining the appropriate magnitude balance and the global direction balance, and propose an innovative methodology named GradCraft in response. |
Yimeng Bai; Yang Zhang; Fuli Feng; Jing Lu; Xiaoxue Zang; Chenyi Lei; Yang Song; |
| 416 | Large Scale Generative AI Text Applied to Sports and Music Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Based on this approach, we introduce, for the first time, an AI commentary system, which was deployed to produce automated narrations for highlight packages at the 2023 US Open, Wimbledon, and Masters tournaments. |
Aaron Baughman; Eduardo Morales; Rahul Agarwal; Gozde Akay; Rogerio Feris; Tony Johnson; Stephen Hammer; Leonid Karlinsky; |
| 417 | LiGNN: Graph Neural Networks at LinkedIn Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present LiGNN, a deployed large-scale Graph Neural Networks (GNNs) Framework. |
Fedor Borisyuk; Shihai He; Yunbo Ouyang; Morteza Ramezani; Peng Du; Xiaochen Hou; Chengming Jiang; Nitin Pasumarthy; Priya Bannur; Birjodh Tiwana; Ping Liu; Siddharth Dangi; Daqi Sun; Zhoutao Pei; Xiao Shi; Sirou Zhu; Qianqi Shen; Kuang-Hsuan Lee; David Stein; Baolei Li; Haichao Wei; Amol Ghoting; Souvik Ghosh; |
| 418 | LiRank: Industrial Large Scale Ranking Models at LinkedIn Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present LiRank, a large-scale ranking framework at LinkedIn that brings to production state-of-the-art modeling architectures and optimization methods. |
Fedor Borisyuk; Mingzhou Zhou; Qingquan Song; Siyu Zhu; Birjodh Tiwana; Ganesh Parameswaran; Siddharth Dangi; Lars Hertel; Qiang Charles Xiao; Xiaochen Hou; Yunbo Ouyang; Aman Gupta; Sheallika Singh; Dan Liu; Hailing Cheng; Lei Le; Jonathan Hung; Sathiya Keerthi; Ruoyan Wang; Fengyu Zhang; Mohit Kothari; Chen Zhu; Daqi Sun; Yun Dai; Xun Luan; Sirou Zhu; Zhiwei Wang; Neil Daftary; Qianqi Shen; Chengming Jiang; Haichao Wei; Maneesh Varshney; Amol Ghoting; Souvik Ghosh; |
| 419 | CompanyKG: A Large-Scale Heterogeneous Graph for Company Similarity Quantification Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper presents CompanyKG (version 2), a large-scale heterogeneous graph developed for fine-grained company similarity quantification and relationship prediction, crucial for applications in the investment industry such as market mapping, competitor analysis, and mergers and acquisitions. |
Lele Cao; Vilhelm von Ehrenheim; Mark Granroth-Wilding; Richard Anselmo Stahl; Andrew McCornack; Armin Catovic; Dhiana Deva Cavalcanti Rocha; |
| 420 | Diffusion Model-based Mobile Traffic Generation with Open Data for Network Planning and Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this article, we propose an Open data-based Diffusion model for mobile traffic generation (OpenDiff), where a multi-positive contrastive learning algorithm is designed to construct conditional information for the diffusion model using entirely publicly available satellite remote sensing images, Point of Interest (POI), and population data. |
Haoye Chai; Tao Jiang; Li Yu; |
| 421 | Enhancing Multi-field B2B Cloud Solution Matching Via Contrastive Pre-training Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, despite their widespread use, the task of identifying appropriate company customers for a specific target solution to the sales team of a solution provider remains a complex business problem that existing matching systems have yet to adequately address. In this work, we study the B2B solution matching problem and identify two main challenges of this scenario: (1) the modeling of complex multi-field features and (2) the limited, incomplete, and sparse transaction data. |
Haonan Chen; Zhicheng Dou; Xuetong Hao; Yunhao Tao; Shiren Song; Zhenli Sheng; |
| 422 | RareBench: Can LLMs Serve As Rare Diseases Specialists? Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To bridge this research gap, we introduce RareBench, a pioneering benchmark designed to systematically evaluate the capabilities of LLMs on 4 critical dimensions within the realm of rare diseases. |
Xuanzhong Chen; Xiaohao Mao; Qihan Guo; Lun Wang; Shuyang Zhang; Ting Chen; |
| 423 | MARLP: Time-series Forecasting Control for Agricultural Managed Aquifer Recharge Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper proposes MARLP, the first end-to-end data-driven control system for Ag-MAR. |
Yuning Chen; Kang Yang; Zhiyu An; Brady Holder; Luke Paloutzian; Khaled M. Bali; Wan Du; |
| 424 | NudgeRank: Digital Algorithmic Nudging for Personalized Health Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we describe NudgeRankTM, an innovative digital algorithmic nudging system designed to foster positive health behaviors on a population-wide scale. |
Jodi Chiam; Aloysius Lim; Ankur Teredesai; |
| 425 | Metric Decomposition in A/B Tests Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In theory, CUPED can be extended to augment a treatment effect estimator utilizing in-experiment data, but practical guidance on how to construct such an augmentation is lacking. In this article, we fill this gap by proposing a new direction for sensitivity improvement via treatment effect augmentation whereby a target metric of interest is decomposed into components with high signal-to-noise disparity. |
Alex Deng; Luke Hagar; Nathaniel T. Stevens; Tatiana Xifara; Amit Gandhi; |
| 426 | MMBee: Live Streaming Gift-Sending Recommendations Via Multi-Modal Fusion and Behaviour Expansion Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, due to the sparsity of gifting behaviors, capturing the preferences and intentions of users is quite difficult. In this work, we propose MMBee based on real-time Multi-Modal Fusion and Behaviour Expansion to address these issues. |
Jiaxin Deng; Shiyao Wang; Yuchen Wang; Jiansong Qi; Liqin Zhao; Guorui Zhou; Gaofeng Meng; |
| 427 | Time-Aware Attention-Based Transformer (TAAT) for Cloud Computing System Failure Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes time-aware attention-based transformer (TAAT), a failure prediction approach that extracts semantic and temporal information simultaneously from log messages and their timestamps. |
Lingfei Deng; Yunong Wang; Haoran Wang; Xuhua Ma; Xiaoming Du; Xudong Zheng; Dongrui Wu; |
| 428 | FNSPID: A Comprehensive Financial News Dataset in Time Series Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Nonetheless, this methodology frequently encounters constraints due to the paucity of extensive datasets that amalgamate both quantitative and qualitative sentiment analyses. To address this challenge, we introduce a large-scale financial dataset, namely, Financial News and Stock Price Integration Dataset (FNSPID). |
Zihan Dong; Xinyu Fan; Zhiyuan Peng; |
| 429 | Enhancing E-commerce Spelling Correction with Fine-Tuned Transformer Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Notably, spelling correction assumes a pivotal role in shaping the user’s search experience by rectifying erroneous query inputs, thus facilitating more accurate retrieval outcomes. Within the scope of this research paper, our aim is to enhance the existing state-of-the-art discriminative model performance with generative modelling strategies while concurrently addressing the engineering concerns associated with real-time online latency, inherent to models of this category. |
Arnab Dutta; Gleb Polushin; Xiaoshuang Zhang; Daniel Stein; |
| 430 | Achieving A Better Tradeoff in Multi-stage Recommender Systems Through Personalization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A key observation we make in this paper is that, all else equal, ranking more items indeed improves the overall objective but has diminishing returns. |
Ariel Evnine; Stratis Ioannidis; Dimitris Kalimeris; Shankar Kalyanaraman; Weiwei Li; Israel Nir; Wei Sun; Udi Weinsberg; |
| 431 | GRILLBot In Practice: Lessons and Tradeoffs Deploying Large Language Models for Adaptable Conversational Task Assistants Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Building on our Open Assistant Toolkit (OAT) framework, we propose a hybrid architecture that leverages Large Language Models (LLMs) and specialised models tuned for specific subtasks requiring very low latency. |
Sophie Fischer; Carlos Gemmell; Niklas Tecklenburg; Iain Mackie; Federico Rossetto; Jeffrey Dalton; |
| 432 | CHILI: Chemically-Informed Large-scale Inorganic Nanomaterials Dataset for Advancing Graph Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we invite the graph ML community to address these open challenges by presenting two new chemically-informed large-scale inorganic (CHILI) nanomaterials datasets. |
Ulrik Friis-Jensen; Frederik L. Johansen; Andy S. Anker; Erik B. Dam; Kirsten M. \O{}. Jensen; Raghavendra Selvan; |
| 433 | Residual Multi-Task Learner for Applied Ranking Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, existing multi-task learning methods encounter two main challenges: some lack explicit modeling of task relationships, resulting in inferior performance, while others have limited applicability due to being computationally intensive, having scalability issues, or relying on strong assumptions. To address these limitations and better fit our real-world scenario, pre-rank in Shopee Search, we introduce in this paper ResFlow, a lightweight multi-task learning framework that enables efficient cross-task information sharing via residual connections between corresponding layers of task networks. |
Cong Fu; Kun Wang; Jiahua Wu; Yizhou Chen; Guangda Huzhang; Yabo Ni; Anxiang Zeng; Zhiming Zhou; |
| 434 | Controllable Multi-Behavior Recommendation for In-Game Skins with Large Sequential Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: These models lack the ability to control predictions of skins that are associated with different scenarios and behaviors. To overcome these limitations, we utilize the pretraining capabilities of Large Sequential Models (LSMs) coupled with a novel stimulus prompt mechanism and build a controllable multi-behavior recommendation (CMBR) model. |
Yanjie Gou; Yuanzhou Yao; Zhao Zhang; Yiqing Wu; Yi Hu; Fuzhen Zhuang; Jiangming Liu; Yongjun Xu; |
| 435 | Transportation Marketplace Rate Forecast Using Signature Transform Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Freight transportation marketplace rates are typically challenging to forecast accurately. In this work, we have developed a novel statistical technique based on signature transforms and have built a predictive and adaptive model to forecast these marketplace rates. |
Haotian Gu; Xin Guo; Timothy L. Jacobs; Philip Kaminsky; Xinyu Li; |
| 436 | LASCA: A Large-Scale Stable Customer Segmentation Approach to Credit Risk Assessment Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, evaluating stability is challenging due to its black-box nature and the computational burden posed by vast user data sets. To address these challenges, this paper proposes a large-scale stable customer segmentation approach named LASCA. |
Yongfeng Gu; Yupeng Wu; Huakang Lu; Xingyu Lu; Hong Qian; Jun Zhou; Aimin Zhou; |
| 437 | Intelligent Agents with LLM-based Process Automation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a novel LLM-based virtual assistant that can automatically perform multi-step operations within mobile apps based on high-level user requests. |
Yanchu Guan; Dong Wang; Zhixuan Chu; Shiyu Wang; Feiyue Ni; Ruihua Song; Chenyi Zhuang; |
| 438 | Multi-task Conditional Attention Network for Conversion Prediction in Logistics Advertising Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Compared to existing online e-commerce advertising, logistics advertising has two significant new characteristics: (i) the complex factors in logistics advertising considering both users’ offline logistics preference and online purchasing profiles; and (ii) data sparsity and mutual relations among multiple steps due to longer advertising conversion processes. To address these challenges, we design MCAC, a Multi-task Conditional Attention network-based logistics advertising Conversion prediction framework, which consists of (i) an offline shipping preference extraction model to extract the user’s offline logistics preference from historical shipping records, and (ii) a multi-task conditional attention-based conversion rate prediction module to model mutual relations among multiple steps in logistics advertising conversion processes. |
Baoshen Guo; Xining Song; Shuai Wang; Wei Gong; Tian He; Xue Liu; |
| 439 | Generative Auto-bidding Via Conditional Diffusion Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To tackle this issue, this paper introduces AI-Generated Bidding (AIGB), a novel paradigm for auto-bidding through generative modeling. In this paradigm, we propose DiffBid, a conditional diffusion modeling approach for bid generation. |
Jiayan Guo; Yusen Huo; Zhilin Zhang; Tianyu Wang; Chuan Yu; Jian Xu; Bo Zheng; Yan Zhang; |
| 440 | SentHYMNent: An Interpretable and Sentiment-Driven Model for Algorithmic Melody Harmonization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we introduce two major novel elements: a nuanced mixture-based representation for musical sentiment, including a web tool to gather data, as well as a sentiment- and theory-driven harmonization model, SentHYMNent. |
Stephen Hahn; Jerry Yin; Rico Zhu; Weihan Xu; Yue Jiang; Simon Mak; Cynthia Rudin; |
| 441 | Learning to Rank for Maps at Airbnb Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes how we rebuilt ranking for maps by revising the mathematical foundations of how users interact with search results. |
Malay Haldar; Hongwei Zhang; Kedar Bellare; Sherry Chen; Soumyadip Banerjee; Xiaotang Wang; Mustafa Abdool; Huiji Gao; Pavan Tapadia; Liwei He; Sanjeev Katariya; |
| 442 | FedSecurity: A Benchmark for Attacks and Defenses in Federated Learning and Federated LLMs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces FedSecurity, an end-to-end benchmark that serves as a supplementary component of the FedML library for simulating adversarial attacks and corresponding defense mechanisms in Federated Learning (FL). |
Shanshan Han; Baturalp Buyukates; Zijian Hu; Han Jin; Weizhao Jin; Lichao Sun; Xiaoyang Wang; Wenxuan Wu; Chulin Xie; Yuhang Yao; Kai Zhang; Qifan Zhang; Yuhui Zhang; Carlee Joe-Wong; Salman Avestimehr; Chaoyang He; |
| 443 | Paths2Pair: Meta-path Based Link Prediction in Billion-Scale Commercial Heterogeneous Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Meanwhile, most methods aggregate information at the node level, potentially leading to the loss of direct connection information between the two nodes. In this paper, we introduce Paths2Pair, a novel framework to address these limitations for link prediction in billion-scale commercial heterogeneous graphs. |
Jinquan Hang; Zhiqing Hong; Xinyue Feng; Guang Wang; Guang Yang; Feng Li; Xining Song; Desheng Zhang; |
| 444 | Rankability-enhanced Revenue Uplift Modeling Framework for Online Marketing Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Moreover, they have neglected to optimize the uplift ranking among different individuals, which is actually the core of uplift modeling. To address such issues, in this paper, we first utilize the zero-inflated lognormal (ZILN) loss to regress the responses and customize the corresponding modeling network, which can be adapted to different existing uplift models. Then, we study the ranking-related uplift modeling error from the theoretical perspective and propose two tighter error bounds as the additional loss terms to the conventional response regression loss. Finally, we directly model the uplift ranking error for the entire population with a listwise uplift ranking loss. |
Bowei He; Yunpeng Weng; Xing Tang; Ziqiang Cui; Zexu Sun; Liang Chen; Xiuqiang He; Chen Ma; |
| 445 | Distributed Harmonization: Federated Clustered Batch Effect Adjustment and Generalization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we develop a novel Cluster ComBat harmonization algorithm, which leverages cluster patterns of the data in different sites and greatly advances the usability of ComBat harmonization. |
Bao Hoang; Yijiang Pang; Siqi Liang; Liang Zhan; Paul M. Thompson; Jiayu Zhou; |
| 446 | Cross-Domain LifeLong Sequential Modeling for Online Click-Through Rate Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose the Lifelong Cross Network (LCN), a novel approach for cross-domain LSM. |
Ruijie Hou; Zhaoyang Yang; Yu Ming; Hongyu Lu; Zhuobin Zheng; Yu Chen; Qinsong Zeng; Ming Chen; |
| 447 | Explainable and Interpretable Forecasts on Non-Smooth Multivariate Time Series for Responsible Gameplay Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a novel deep Actionable Forecasting Network (AFN), which addresses the inter-dependent challenges associated with three exclusive objectives – 1) forecasting accuracy; 2) smooth comprehensible trajectory and 3) explanations via multi-dimensional input features while tackling the challenges introduced by our non-smooth temporal data, together in one single solution. |
Hussain Jagirdar; Rukma Talwadker; Aditya Pareek; Pulkit Agrawal; Tridib Mukherjee; |
| 448 | Personalised Drug Identifier for Cancer Treatment with Transformers Using Auxiliary Information Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Further, they do not utilize auxiliary information (like patient survival) for model training. We address these limitations through a novel transformer-based method, which surpasses the performance of state-of-the-art DRP models on benchmark data. |
Aishwarya Jayagopal; Hansheng Xue; Ziyang He; Robert J. Walsh; Krishna Kumar Hariprasannan; David Shao Peng Tan; Tuan Zea Tan; Jason J. Pitt; Anand D. Jeyasekharan; Vaibhav Rajan; |
| 449 | Learning to Bid The Interest Rate in Online Unsecured Personal Loans Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an algorithm named AutoInterest, which is a modification of the dual gradient descent algorithm. |
Dong Jun Jee; Seung Jung Jin; Ji Hoon Yoo; Byunggyu Ahn; |
| 450 | Personalized Product Assortment with Real-time 3D Perception and Bayesian Payoff Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Additionally, existing strategies rely on syndicated data, which tends to be aggregated, low resolution, and suffer from high latency. To solve these challenges, we introduce a real-time recommendation system, which we call EdgeRec3D. |
Porter Jenkins; Michael Selander; J. Stockton Jenkins; Andrew Merrill; Kyle Armstrong; |
| 451 | Decomposed Attention Segment Recurrent Neural Network for Orbit Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose the Decomposed Attention Segment Recurrent Neural Network (DASR) model, adding two key components, Multi-Head Attention and Tensor Train Decomposition, to SegRNN for orbit prediction. |
SeungWon Jeong; Soyeon Woo; Daewon Chung; Simon S. Woo; Youjin Shin; |
| 452 | Learning Metrics That Maximise Power for Accelerated A/B-Tests Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We show that existing approaches are prone to overfitting, in that higher average metric sensitivity does not imply improved type-II errors, and propose to instead minimise the p-values a metric would have produced on a log of past experiments. We collect such datasets from two social media applications with over 160 million Monthly Active Users each, totalling over 153 A/B-pairs. |
Olivier Jeunen; Aleksei Ustimenko; |
| 453 | ERASE: Benchmarking Feature Selection Methods for Deep Recommender Systems Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This approach is typically computationally infeasible for identifying the optimal hyperparameters and overlooks evaluating the robustness and stability of these methods. To bridge these gaps, this paper presents ERASE, a comprehensive bEnchmaRk for feAture SElection for DRS. ERASE comprises a thorough evaluation of eleven feature selection methods, covering both traditional and deep learning approaches, across four public datasets, private industrial datasets, and a real-world commercial platform, achieving significant enhancement. |
Pengyue Jia; Yejing Wang; Zhaocheng Du; Xiangyu Zhao; Yichao Wang; Bo Chen; Wanyu Wang; Huifeng Guo; Ruiming Tang; |
| 454 | Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite numerous efforts have been made on congestion prediction, most of them fall short in handling heterogeneous and dynamic spatio-temporal dependencies (e.g., periodic and non-periodic congestions), particularly in the presence of noisy and incomplete traffic data. In this paper, we introduce a Congestion Prediction Mixture-of-Experts, CP-MoE, to address the above challenges. |
Wenzhao Jiang; Jindong Han; Hao Liu; Tao Tao; Naiqiang Tan; Hui Xiong; |
| 455 | RJUA-MedDQA: A Multimodal Benchmark for Medical Document Question Answering and Clinical Reasoning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we establish a comprehensive benchmark in the field of medical specialization and introduced RJUA-MedDQA, which contains 2000 real-world Chinese medical report images poses several challenges: comprehensively interpreting imgage content across a wide variety of challenging layouts, possessing the numerical reasoning ability to identify abnormal indicators and demonstrating robust clinical reasoning ability to provide the statement of disease diagnosis, status and advice based on a collection of medical contexts. |
Congyun Jin; Ming Zhang; Weixiao Ma; Yujiao Li; Yingbo Wang; Yabo Jia; Yuliang Du; Tao Sun; Haowen Wang; Cong Fan; Jinjie Gu; Chenfei Chi; Xiangguo Lv; Fangzhou Li; Wei Xue; Yiran Huang; |
| 456 | Large Scale Hierarchical Industrial Demand Time-Series Forecasting Incorporating Sparsity Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Further, they do not scale well to the large size of the real-world hierarchy typically unseen in benchmarks used in literature. We resolve both these challenges by proposing HAILS, a novel probabilistic hierarchical model that enables accurate and calibrated probabilistic forecasts across the hierarchy by adaptively modeling sparse and dense time-series with different distributional assumptions and reconciling them to adhere to hierarchical constraints. |
Harshavardhan Kamarthi; Aditya B. Sasanur; Xinjie Tong; Xingyu Zhou; James Peters; Joe Czyzyk; B. Aditya Prakash; |
| 457 | False Positives in A/B Tests Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We offer a modified procedure for experimentation, based in sequential group testing, that selectively extends experiments to reduce false positives, increase power, at a small increase to runtime. |
Ron Kohavi; Nanyu Chen; |
| 458 | Offline Reinforcement Learning for Optimizing Production Bidding Policies Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a generalizable approach to optimizing bidding policies in production environments by learning from real data using offline reinforcement learning. |
Dmytro Korenkevych; Frank Cheng; Artsiom Balakir; Alex Nikulkov; Lingnan Gao; Zhihao Cen; Zuobing Xu; Zheqing Zhu; |
| 459 | FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Despite the aforementioned advantages of FL, fine-tuning LLMs in FL settings still lacks adequate support from the existing frameworks and, therefore, faces challenges in optimizing the consumption of significant communication and computational resources, preparing various data for different tasks, and satisfying diverse information protection demands. In this paper, we discuss these challenges and introduce our package FederatedScope-LLM (FS-LLM) as a main contribution, which consists: (1) We build a complete end-to-end benchmarking pipeline under real-world scenarios, automizing the processes of dataset preprocessing, federated fine-tuning execution or simulation, and performance evaluation; (2) We provide comprehensive and off-the-shelf federated parameter-efficient fine-tuning (PEFT) algorithm implementations and versatile programming interfaces for future extension, enhancing the capabilities of LLMs in FL scenarios with low communication and computation costs, even without accessing the full model; (3) We adopt several accelerating and resource-efficient operators, and provide flexible pluggable sub-routines for interdisciplinary study. |
Weirui Kuang; Bingchen Qian; Zitao Li; Daoyuan Chen; Dawei Gao; Xuchen Pan; Yuexiang Xie; Yaliang Li; Bolin Ding; Jingren Zhou; |
| 460 | Know, Grow, and Protect Net Worth: Using ML for Asset Protection By Preventing Overdraft Fees Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: These overdraft fees are an excessive financial burden and lead to cascading overdraft fees trapping customers in financial hardship. To address this problem, we have created an ML-driven overdraft early warning system (ODEWS) that assesses a customer’s risk of overdrafting within the next week using their banking and transaction data in the Mint app. |
Avishek Kumar; Tyson Silver; |
| 461 | Causal Machine Learning for Cost-Effective Allocation of Development Aid Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we develop a causal machine learning framework for predicting heterogeneous treatment effects of aid disbursements to inform effective aid allocation. |
Milan Kuzmanovic; Dennis Frauen; Tobias Hatt; Stefan Feuerriegel; |
| 462 | AutoWebGLM: A Large Language Model-based Web Navigating Agent Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Large language models (LLMs) have fueled many intelligent web agents, but most existing ones perform far from satisfying in real-world web navigation tasks due to three factors: (1) the complexity of HTML text data (2) versatility of actions on webpages, and (3) task difficulty due to the open-domain nature of the web. In light of these challenges, we develop the open AutoWebGLM based on ChatGLM3-6B. |
Hanyu Lai; Xiao Liu; Iat Long Iong; Shuntian Yao; Yuxuan Chen; Pengbo Shen; Hao Yu; Hanchen Zhang; Xiaohan Zhang; Yuxiao Dong; Jie Tang; |
| 463 | Contextual Distillation Model for Diversified Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose Contextual Distillation Model (CDM), an efficient recommendation model that addresses diversification, suitable for the deployment in all stages of industrial recommendation pipelines. |
Fan Li; Xu Si; Shisong Tang; Dingmin Wang; Kunyan Han; Bing Han; Guorui Zhou; Yang Song; Hechang Chen; |
| 464 | Chromosomal Structural Abnormality Diagnosis By Homologous Similarity Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In normal cases, homologous chromosomes share identical structures, with the exception that one of them is abnormal. Therefore, we propose an adaptive method to align homologous chromosomes and diagnose structural abnormalities through homologous similarity. |
Juren Li; Fanzhe Fu; Ran Wei; Yifei Sun; Zeyu Lai; Ning Song; Xin Chen; Yang Yang; |
| 465 | SEFraud: Graph-based Self-Explainable Fraud Detection Via Interpretative Mask Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, post-hoc explanations can not facilitate the model predictions and the computational cost of these methods cannot meet practical requirements, thus limiting their application in real-world scenarios. To address these issues, we propose SEFraud, a novel graph-based self-explainable fraud detection framework that simultaneously tackles fraud detection and result in interpretability. |
Kaidi Li; Tianmeng Yang; Min Zhou; Jiahao Meng; Shendi Wang; Yihui Wu; Boshuai Tan; Hu Song; Lujia Pan; Fan Yu; Zhenli Sheng; Yunhai Tong; |
| 466 | Text Matching Indexers in Taobao Search Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Recent successes involve reducing the size (pruning) of the inverted index but the construction and deployment of lossless static index pruning in practical product search still pose non-trivial challenges.In this work, we introduce a novel SM art INDexing (SMIND) solution in Taobao product search. |
Sen Li; Fuyu Lv; Ruqing Zhang; Dan Ou; Zhixuan Zhang; Maarten de Rijke; |
| 467 | UrbanGPT: Spatio-Temporal Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Consequently, it becomes necessary to build a spatio-temporal model that can exhibit strong generalization capabilities across diverse spatio-temporal learning scenarios.Taking inspiration from the remarkable achievements of large language models (LLMs), our objective is to create a spatio-temporal LLM that can exhibit exceptional generalization capabilities across a wide range of downstream urban tasks. |
Zhonghang Li; Lianghao Xia; Jiabin Tang; Yong Xu; Lei Shi; Long Xia; Dawei Yin; Chao Huang; |
| 468 | Harvesting Efficient On-Demand Order Pooling from Skilled Couriers: Enhancing Graph Representation Learning for Refining Real-time Many-to-One Assignments Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Nevertheless, delivery behaviors of skilled couriers (SCs) who know the environment well, can improve system awareness and effectively inform decisions. Hence a SC delivery network (SCDN) is constructed, based on an enhanced attributed heterogeneous network embedding approach tailored for OFD. |
Yile Liang; Jiuxia Zhao; Donghui Li; Jie Feng; Chen Zhang; Xuetao Ding; Jinghua Hao; Renqing He; |
| 469 | An Open and Large-Scale Dataset for Multi-Modal Climate Change-aware Crop Yield Predictions Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: While AI-for-science approaches have exhibited promising achievements in solving many scientific problems such as drug discovery, precipitation nowcasting, etc., the development of deep learning models for predicting crop yields is constantly hindered by the lack of an open and large-scale deep learning-ready dataset with multiple modalities to accommodate sufficient information. To remedy this, we introduce the CropNet dataset, the first terabyte-sized, publicly available, and multi-modal dataset specifically targeting climate change-aware crop yield predictions for the contiguous United States (U.S.) continent at the county level. |
Fudong Lin; Kaleb Guillot; Summer Crawford; Yihe Zhang; Xu Yuan; Nian-Feng Tzeng; |
| 470 | Hyper-Local Deformable Transformers for Text Spotting on Historical Maps Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes PALETTE, an end-to-end text spotter for scanned historical maps of a wide variety. |
Yijun Lin; Yao-Yi Chiang; |
| 471 | Deep Bag-of-Words Model: An Efficient and Interpretable Relevance Architecture for Chinese E-Commerce Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we raise deep Bag-o f-Words (DeepBoW) model, an efficient and interpretable relevance architecture for Chinese e-commerce. |
Zhe Lin; Jiwei Tan; Dan Ou; Xi Chen; Shaowei Yao; Bo Zheng; |
| 472 | Understanding The Ranking Loss for Recommendation with Sparse User Feedback Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we uncover a new challenge associated with the BCE loss in scenarios where positive feedback is sparse: the issue of gradient vanishing for negative samples. |
Zhutian Lin; Junwei Pan; Shangyu Zhang; Ximei Wang; Xi Xiao; Shudong Huang; Lei Xiao; Jie Jiang; |
| 473 | Source Localization for Cross Network Information Diffusion Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we propose a novel method, namely CNSL, to handle the three primary challenges. |
Chen Ling; Tanmoy Chowdhury; Jie Ji; Sirui Li; Andreas Z\{u}fle; Liang Zhao; |
| 474 | MFTCoder: Boosting Code LLMs with Multitask Fine-Tuning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Furthermore, these approaches failed to leverage the inherent interconnectedness among different code-related tasks. To overcome these limitations, we present a multi-task fine-tuning framework, MFTCoder, that enables simultaneous and parallel fine-tuning on multiple tasks. |
Bingchang Liu; Chaoyu Chen; Zi Gong; Cong Liao; Huan Wang; Zhichao Lei; Ming Liang; Dajun Chen; Min Shen; Hailian Zhou; Wei Jiang; Hang Yu; Jianguo Li; |
| 475 | Beyond Binary Preference: Leveraging Bayesian Approaches for Joint Optimization of Ranking and Calibration Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This is because the binary click feedback leads to a large number of ties, which renders high data sparsity. In this paper, we propose an effective data augmentation strategy, named Beyond Binary Preference (BBP) training framework, to address this problem. |
Chang Liu; Qiwei Wang; Wenqing Lin; Yue Ding; Hongtao Lu; |
| 476 | DAG: Deep Adaptive and Generative K-Free Community Detection on Attributed Graphs Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we investigate the community detection problem without prior K, referred to as K-Free Community Detection problem. |
Chang Liu; Yuwen Yang; Yue Ding; Hongtao Lu; Wenqing Lin; Ziming Wu; Wendong Bi; |
| 477 | Towards Automatic Evaluation for LLMs’ Clinical Capabilities: Metric, Data, and Algorithm Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, current evaluation methods heavily rely on labor-intensive human participation to achieve human-preferred judgements. To overcome this challenge, we propose an automatic evaluation paradigm tailored to assess the LLMs’ capabilities in delivering clinical services, e.g., disease diagnosis and treatment. |
Lei Liu; Xiaoyan Yang; Fangzhou Li; Chenfei Chi; Yue Shen; Shiwei Lyu; Ming Zhang; Xiaowei Ma; Xiangguo Lv; Liya Ma; Zhiqiang Zhang; Wei Xue; Yiran Huang; Jinjie Gu; |
| 478 | GRAM: Generative Retrieval Augmented Matching of Data Schemas in The Context of Data Security Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Given its significance in the realm of database systems, schema matching has been under investigation since the 2000s. This study revisits this foundational problem within the context of large language models. |
Xuanqing Liu; Runhui Wang; Yang Song; Luyang Kong; |
| 479 | EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we propose EmoLLMs, the first series of open-sourced instruction-following LLMs for comprehensive affective analysis based on fine-tuning various LLMs with instruction data, the first multi-task affective analysis instruction dataset (AAID) with 234K data samples based on 3 classification tasks and 2 regression tasks to support LLM instruction tuning, and a comprehensive affective evaluation benchmark (AEB) with 8 regression tasks and 6 classification tasks from various sources and domains to test the generalization ability of LLMs. |
Zhiwei Liu; Kailai Yang; Qianqian Xie; Tianlin Zhang; Sophia Ananiadou; |
| 480 | Modeling User Retention Through Generative Flow Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, optimizing this user retention behavior is non-trivial and poses several challenges including the intractable leave-and-return user activities, the sparse and delayed signal, and the uncertain relations between users’ retention and their immediate feedback towards each item in the recommendation list. In this work, we regard the retention signal as an overall estimation of the user’s end-of-session satisfaction and propose to estimate this signal through a probabilistic flow. |
Ziru Liu; Shuchang Liu; Bin Yang; Zhenghai Xue; Qingpeng Cai; Xiangyu Zhao; Zijian Zhang; Lantao Hu; Han Li; Peng Jiang; |
| 481 | MISP: A Multimodal-based Intelligent Server Failure Prediction Model for Cloud Computing Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Addressing these challenges, this paper presents an industrial-scale, comprehensive dataset for server failure prediction, comprising nearly 80 types of structured and unstructured data sourced from real-world industrial cloud systems 1. Building on this resource, we introduce MISP, a model that leverages multimodal fusion techniques for server failure prediction. |
Xianting Lu; Yunong Wang; Yu Fu; Qi Sun; Xuhua Ma; Xudong Zheng; Cheng Zhuo; |
| 482 | Integrating System State Into Spatio Temporal Graph Neural Network for Microservice Workload Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This inefficiency necessitates the development of dynamic, accurate workload prediction methods to improve resource allocation. In response to this challenge, we present STAMP, a Spatio Temporal Graph Network for Microservice Workload Prediction. |
Yang Luo; Mohan Gao; Zhemeng Yu; Haoyuan Ge; Xiaofeng Gao; Tengwei Cai; Guihai Chen; |
| 483 | FusionSF: Fuse Heterogeneous Modalities in A Vector Quantized Framework for Robust Solar Power Forecasting Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a multi-modality fusion framework to integrate historical power data, numerical weather prediction, and satellite images, significantly improving forecast performance. |
Ziqing Ma; Wenwei Wang; Tian Zhou; Chao Chen; Bingqing Peng; Liang Sun; Rong Jin; |
| 484 | EEG2Rep: Enhancing Self-supervised EEG Representation Through Informative Masked Inputs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Self-supervised approaches for electroencephalography (EEG) representation learning face three specific challenges inherent to EEG data: (1) The low signal-to-noise ratio which challenges the quality of the representation learned, (2) The wide range of amplitudes from very small to relatively large due to factors such as the inter-subject variability, risks the models to be dominated by higher amplitude ranges, and (3) The absence of explicit segmentation in the continuous-valued sequences which can result in less informative representations. To address these challenges, we introduce EEG2Rep, a self-prediction approach for self-supervised representation learning from EEG. |
Navid Mohammadi Foumani; Geoffrey Mackellar; Soheila Ghane; Saad Irtza; Nam Nguyen; Mahsa Salehi; |
| 485 | Valuing An Engagement Surface Using A Large Scale Dynamic Causal Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Understanding the causal effect of engagement surfaces on value driven for customers and businesses remains an open scientific question. In this paper, we develop a dynamic causal model at scale to disentangle value attributable to an ES, and to assess its effectiveness. |
Abhimanyu Mukerji; Sushant More; Ashwin Viswanathan Kannan; Lakshmi Ravi; Hua Chen; Naman Kohli; Chris Khawand; Dinesh Mandalapu; |
| 486 | Ads Recommendation in A Collapsed and Entangled World Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We present Tencent’s ads recommendation system and examine the challenges and practices of learning appropriate recommendation representations. |
Junwei Pan; Wei Xue; Ximei Wang; Haibin Yu; Xun Liu; Shijie Quan; Xueming Qiu; Dapeng Liu; Lei Xiao; Jie Jiang; |
| 487 | Detecting Abnormal Operations in Concentrated Solar Power Plants from Irregular Sequences of Thermal Images Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Our goal is to develop a method to extract useful representations from high-dimensional thermal images for AD. |
Sukanya Patra; Nicolas Sournac; Souhaib Ben Taieb; |
| 488 | Spatio-Temporal Consistency Enhanced Differential Network for Interpretable Indoor Temperature Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we propose a Spatio-Temporal Consistency enhanced Differential Network (CONST) for interpretable indoor temperature prediction. |
Dekang Qi; Xiuwen Yi; Chengjie Guo; Yanyong Huang; Junbo Zhang; Tianrui Li; Yu Zheng; |
| 489 | Addressing Shortcomings in Fair Graph Learning Datasets: Towards A New Benchmark Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In such cases, even a basic Multilayer Perceptron (MLP) can outperform Graph Neural Networks (GNNs) in both utility and fairness. In this work, we illustrate that many datasets fail to provide meaningful information in the edges, which may challenge the necessity of using graph structures in these problems. |
Xiaowei Qian; Zhimeng Guo; Jialiang Li; Haitao Mao; Bingheng Li; Suhang Wang; Yao Ma; |
| 490 | Class-incremental Learning for Time Series: Benchmark and Evaluation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To this end, we first present an overview of the Time Series Class-incremental Learning (TSCIL) problem, highlight its unique challenges, and cover the advanced methodologies. |
Zhongzheng Qiao; Quang Pham; Zhen Cao; Hoang H. Le; P. N. Suganthan; Xudong Jiang; Savitha Ramasamy; |
| 491 | Non-autoregressive Generative Models for Reranking Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To tackle challenges such as sparse training samples and dynamic candidates, we introduce a matching model. |
Yuxin Ren; Qiya Yang; Yichun Wu; Wei Xu; Yalong Wang; Zhiqiang Zhang; |
| 492 | Leveraging Exposure Networks for Detecting Fake News Sources Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we develop a novel machine-learning methodology for detecting fake news sources using active learning, and examine the contribution of network, audience, and text features to the model accuracy. |
Maor Reuben; Lisa Friedland; Rami Puzis; Nir Grinberg; |
| 493 | Tackling Concept Shift in Text Classification Using Entailment-style Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a reformulation, converting vanilla classification into an entailment-style problem that requires significantly less data to re-train the text classifier to adapt to new concepts. |
Sumegh Roychowdhury; Karan Gupta; Siva Rajesh Kasa; Prasanna Srinivasa Murthy; |
| 494 | Hierarchical Knowledge Guided Fault Intensity Diagnosis of Complex Industrial Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To capture and explore dependencies, we propose a hierarchical knowledge guided fault intensity diagnosis framework (HKG) inspired by the tree of thought, which is amenable to any representation learning methods. |
Yu Sha; Shuiping Gou; Bo Liu; Johannes Faber; Ningtao Liu; Stefan Schramm; Horst Stoecker; Thomas Steckenreiter; Domagoj Vnucec; Nadine Wetzstein; Andreas Widl; Kai Zhou; |
| 495 | Optimizing Novelty of Top-k Recommendations Using Large Language Models and Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, novel items, by definition, do not have any user feedback data. Given the semantic capabilities of large language models, we address these problems using a reinforcement learning (RL) formulation where large language models provide feedback for the novel items. |
Amit Sharma; Hua Li; Xue Li; Jian Jiao; |
| 496 | Measuring An LLM’s Proficiency at Using APIs: A Query Generation Strategy Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we pose the following question: what does it mean to say that an LLM is proficient at using a set of APIs? |
Ying Sheng; Sudeep Gandhe; Bhargav Kanagal; Nick Edmonds; Zachary Fisher; Sandeep Tata; Aarush Selvan; |
| 497 | Lumos: Empowering Multimodal LLMs with Scene Text Recognition Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While building Lumos, we encountered numerous challenges related to STR quality, overall latency, and model inference. In this paper, we delve into those challenges, and discuss the system architecture, design choices, and modeling techniques employed to overcome these obstacles. |
Ashish Shenoy; Yichao Lu; Srihari Jayakumar; Debojeet Chatterjee; Mohsen Moslehpour; Pierce Chuang; Abhay Harpale; Vikas Bhardwaj; Di Xu; Shicong Zhao; Longfang Zhao; Ankit Ramchandani; Xin Luna Dong; Anuj Kumar; |
| 498 | From Variability to Stability: Advancing RecSys Benchmarking Practices Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: However, this approach may fail to holistically reflect their effectiveness due to the significant impact of dataset characteristics on algorithm performance. Addressing this deficiency, this paper introduces a novel benchmarking methodology to facilitate a fair and robust comparison of RecSys algorithms, thereby advancing evaluation practices. |
Valeriy Shevchenko; Nikita Belousov; Alexey Vasilev; Vladimir Zholobov; Artyom Sosedka; Natalia Semenova; Anna Volodkevich; Andrey Savchenko; Alexey Zaytsev; |
| 499 | Improving Ego-Cluster for Network Effect Measurement Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper discusses a new cluster-level experimentation methodology for measuring creator-side metrics in the context of A/B experiments. |
Wentao Su; Weitao Duan; |
| 500 | Multi-Task Neural Linear Bandit for Exploration in Recommender Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study an efficient bandit algorithm tailored to multi-task recommender systems, named Multi-task Neural Linear Bandit (mtNLB). |
Yi Su; Haokai Lu; Yuening Li; Liang Liu; Shuchao Bi; Ed H. Chi; Minmin Chen; |
| 501 | Spending Programmed Bidding: Privacy-friendly Bid Optimization with ROI Constraint in Online Advertising Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Privacy protection strategies, including event aggregation and reporting delays, hinder access to detailed and instantaneous feedback data, thus incapacitating traditional identity-revealing attribution techniques. In this paper, we introduces a novel Spending Programmed Bidding (SPB) framework to navigate these challenges. |
Yumin Su; Min Xiang; Yifei Chen; Yanbiao Li; Tian Qin; Hongyi Zhang; Yasong Li; Xiaobing Liu; |
| 502 | MGMatch: Fast Matchmaking with Nonlinear Objective and Constraints Via Multimodal Deep Graph Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel deep learning method for high-quality matchmaking in real-time. |
Yu Sun; Kai Wang; Zhipeng Hu; Runze Wu; Yaoxin Wu; Wen Song; Xudong Shen; Tangjie Lv; Changjie Fan; |
| 503 | PEMBOT: Pareto-Ensembled Multi-task Boosted Trees Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we develop PEMBOT, a novel Pareto-based multi-task classification framework using a gradient boosted tree architecture. |
Gokul Swamy; Anoop Saladi; Arunita Das; Shobhit Niranjan; |
| 504 | Enhancing Personalized Headline Generation Via Offline Goal-conditioned Reinforcement Learning with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a novel framework to generate personalized news headlines using LLMs with extensive online exploration. |
Xiaoyu Tan; Leijun Cheng; Xihe Qiu; Shaojie Shi; Yuan Cheng; Wei Chu; Yinghui Xu; Yuan Qi; |
| 505 | Beimingwu: A Learnware Dock System Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This paper proposes Beimingwu, the first open-source learnware dock system, providing foundational support for future research. |
Zhi-Hao Tan; Jian-Dong Liu; Xiao-Dong Bi; Peng Tan; Qin-Cheng Zheng; Hai-Tian Liu; Yi Xie; Xiao-Chuan Zou; Yang Yu; Zhi-Hua Zhou; |
| 506 | Multi-objective Learning to Rank By Model Distillation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a distillation-based ranking solution for multi-objective ranking, which optimizes the end-to-end ranking system at Airbnb across multiple ranking models on different objectives along with various considerations to optimize training and serving efficiency to meet industry standards. |
Jie Tang; Huiji Gao; Liwei He; Sanjeev Katariya; |
| 507 | Business Policy Experiments Using Fractional Factorial Designs: Consumer Retention on DoorDash Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper investigates an approach to both speed up business decision-making and lower the cost of learning through experimentation by factorizing business policies and employing fractional factorial experimental designs for their evaluation. |
Yixin Tang; Yicong Lin; Navdeep S. Sahni; |
| 508 | Choosing A Proxy Metric from Past Experiments Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a new statistical framework to both define and construct an optimal proxy metric for use in a homogeneous population of randomized experiments. |
Nilesh Tripuraneni; Lee Richardson; Alexander D’Amour; Jacopo Soriano; Steve Yadlowsky; |
| 509 | R-Eval: A Unified Toolkit for Evaluating Domain Knowledge of Retrieval Augmented Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we address the challenges of evaluating RALLMs by introducing the R-Eval toolkit, a Python toolkit designed to streamline the evaluation of different RAG workflows in conjunction with LLMs. |
Shangqing Tu; Yuanchun Wang; Jifan Yu; Yuyang Xie; Yaran Shi; Xiaozhi Wang; Jing Zhang; Lei Hou; Juanzi Li; |
| 510 | Chaining Text-to-Image and Large Language Model: A Novel Approach for Generating Personalized E-commerce Banners Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we demonstrate the use of text-to-image models for generating personalized web banners with dynamic content for online shoppers based on their interactions. |
Shanu Vashishtha; Abhinav Prakash; Lalitesh Morishetti; Kaushiki Nag; Yokila Arora; Sushant Kumar; Kannan Achan; |
| 511 | TnT-LLM: Text Mining at Scale with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This is particularly challenging when the label space is under-specified and large-scale data annotations are unavailable. In this paper, we address these challenges with Large Language Models (LLMs), whose prompt-based interface facilitates the induction and use of large-scale pseudo labels. |
Mengting Wan; Tara Safavi; Sujay Kumar Jauhar; Yujin Kim; Scott Counts; Jennifer Neville; Siddharth Suri; Chirag Shah; Ryen W. White; Longqi Yang; Reid Andersen; Georg Buscher; Dhruv Joshi; Nagu Rangan; |
| 512 | BacktrackSTL: Ultra-Fast Online Seasonal-Trend Decomposition with Backtrack Technique Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, existing algorithms either fail to handle long-period time series (such as OnlineSTL), or need time-consuming iterative processes (such as OneShotSTL). Therefore, we propose BacktrackSTL, the first non-iterative online STD algorithm with period-independent O(1) update complexity. |
Haoyu Wang; Hongke Guo; Zhaoliang Zhu; You Zhang; Yu Zhou; Xudong Zheng; |
| 513 | Know Your Needs Better: Towards Structured Understanding of Marketer Demands with Analogical Reasoning Augmented LLMs Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we explore a new way for user targeting, where non-expert marketers could select their target users solely given demands in natural language form. |
Junjie Wang; Dan Yang; Binbin Hu; Yue Shen; Wen Zhang; Jinjie Gu; |
| 514 | ADSNet: Cross-Domain LTV Prediction with An Adaptive Siamese Network in Advertising Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To tackle the issue of data distribution shift between internal and external platforms, we introduce an Adaptive Difference Siamese Network (ADSNet), which employs cross-domain transfer learning to prevent negative transfer. |
Ruize Wang; Hui Xu; Ying Cheng; Qi He; Xing Zhou; Rui Feng; Wei Xu; Lei Huang; Jie Jiang; |
| 515 | LiMAML: Personalization of Deep Recommender Models Via Meta Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce an innovative meta-learning solution tailored to the personalization of models for individual members and other entities, coupled with the frequent updates based on the latest user interaction signals. |
Ruofan Wang; Prakruthi Prabhakar; Gaurav Srivastava; Tianqi Wang; Zeinab S. Jalali; Varun Bharill; Yunbo Ouyang; Aastha Nigam; Divya Venugopalan; Aman Gupta; Fedor Borisyuk; Sathiya Keerthi; Ajith Muralidharan; |
| 516 | COMET: NFT Price Prediction with Wallet Profiling Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Moreover, the influence of users’ multi-behaviour transactions that are publicly accessible on NFT price is still not explored and exhibits challenges. In this paper, we address these gaps by presenting a practical and hierarchical problem definition. |
Tianfu Wang; Liwei Deng; Chao Wang; Jianxun Lian; Yue Yan; Nicholas Jing Yuan; Qi Zhang; Hui Xiong; |
| 517 | Future Impact Decomposition in Request-level Recommendations Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we demonstrate that an item-level optimization approach can better utilize item characteristics and optimize the policy’s performance even under the request-level MDP. |
Xiaobei Wang; Shuchang Liu; Xueliang Wang; Qingpeng Cai; Lantao Hu; Han Li; Peng Jiang; Kun Gai; Guangming Xie; |
| 518 | Mitigating Pooling Bias in E-commerce Search Via False Negative Estimation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Unfortunately, current methods introduce pooling bias by mistakenly sampling false negatives, diminishing performance and business impact. To address this, we present Bias-mitigating Hard Negative Sampling (BHNS), a novel negative sampling strategy tailored to identify and adjust for false negatives, building upon our original False Negative Estimation algorithm. |
Xiaochen Wang; Xiao Xiao; Ruhan Zhang; Xuan Zhang; Taesik Na; Tejaswi Tenneti; Haixun Wang; Fenglong Ma; |
| 519 | Know in AdVance: Linear-Complexity Forecasting of Ad Campaign Performance with Evolving User Interest Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We propose AdVance, a time-aware framework that integrates local auction-level and global campaign-level modeling. |
Xiaoyu Wang; Yonghui Guo; Hui Sheng; Peili Lv; Chi Zhou; Wei Huang; Shiqin Ta; Dongbo Huang; Xiujin Yang; Lan Xu; Hao Zhou; Yusheng Ji; |
| 520 | Neural Optimization with Adaptive Heuristics for Intelligent Marketing System Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a general framework for marketing AI systems, the Neural Optimization with Adaptive Heuristics (NOAH) framework. |
Changshuai Wei; Benjamin Zelditch; Joyce Chen; Andre Assuncao Silva T Ribeiro; Jingyi Kenneth Tay; Borja Ocejo Elizondo; Sathiya Keerthi Selvaraj; Aman Gupta; Licurgo Benemann De Almeida; |
| 521 | Enhancing Pre-Ranking Performance: Tackling Intermediary Challenges in Multi-Stage Cascading Recommendation Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce new metrics for pre-ranking evaluation, while experiments confirm the effectiveness of our framework. |
Jianping Wei; Yujie Zhou; Zhengwei Wu; Ziqi Liu; |
| 522 | On Finding Bi-objective Pareto-optimal Fraud Prevention Rule Sets for Fintech Applications Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: This intermediate stage greatly simplifies the selection criteria and increases the flexibility of Stage 2. For this intermediate stage, we propose a heuristic-based framework called PORS and we identify that the core of PORS is the problem of solution selection on the front (SSF). |
Chengyao Wen; Yin Lou; |
| 523 | Nested Fusion: A Method for Learning High Resolution Latent Structure of Multi-Scale Measurement Data on Mars Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we introduce Nested Fusion, a method to combine arbitrarily layered datasets of different resolutions and produce a latent distribution at the highest possible resolution, encoding complex interrelationships between different measurements and scales. |
Austin P. Wright; Scott Davidoff; Duen Horng Chau; |
| 524 | TrajRecovery: An Efficient Vehicle Trajectory Recovery Framework Based on Urban-Scale Traffic Camera Records Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, existing methods face two challenges: i) the inability to process city-wide vehicle trajectories, and ii) the dependence on a substantial amount of accurate GPS trajectories for model training, leading to poor generalization ability. To address these issues, we propose a novel trajectory recovery system based on vehicle snapshots captured by traffic cameras, named TrajRecovery. |
Dongen Wu; Ziquan Fang; Qichen Sun; Lu Chen; Haiyang Hu; Fei Wang; Yunjun Gao; |
| 525 | LaDe: The First Comprehensive Last-mile Express Dataset from Industry Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce LaDe, the first publicly available last-mile express dataset with millions of packages from the industry. |
Lixia Wu; Haomin Wen; Haoyuan Hu; Xiaowei Mao; Yutong Xia; Ergang Shan; Jianbin Zheng; Junhong Lou; Yuxuan Liang; Liuqing Yang; Roger Zimmermann; Youfang Lin; Huaiyu Wan; |
| 526 | Xinyu: An Efficient LLM-based System for Commentary Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce Xinyu, an efficient LLM-based system designed to assist commentators in generating Chinese commentaries. |
Yiquan Wu; Bo Tang; Chenyang Xi; Yu Yu; Pengyu Wang; Yifei Liu; Kun Kuang; Haiying Deng; Zhiyu Li; Feiyu Xiong; Jie Hu; Peng Cheng; Zhonghao Wang; Yi Wang; Yi Luo; Mingchuan Yang; |
| 527 | DuMapNet: An End-to-End Vectorization System for City-Scale Lane-Level Map Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: These obstacles result in labor-intensive human annotation and high maintenance costs. This paper overcomes these limitations and presents an industrial-grade solution named DuMapNet that outputs standardized, vectorized map elements and their topology in an end-to-end paradigm. |
Deguo Xia; Weiming Zhang; Xiyan Liu; Wei Zhang; Chenting Gong; Jizhou Huang; Mengmeng Yang; Diange Yang; |
| 528 | VecAug: Unveiling Camouflaged Frauds with Cohort Augmentation for Enhanced Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In contrast, sequence-based approaches analyze users’ behavioral patterns, offering robustness against tampering but overlooking the interactions between similar users. Inspired by cohort analysis in retention and healthcare, this paper introduces VecAug, a novel cohort-augmented learning framework that addresses these challenges by enhancing the representation learning of target users with personalized cohort information. |
Fei Xiao; Shaofeng Cai; Gang Chen; H. V. Jagadish; Beng Chin Ooi; Meihui Zhang; |
| 529 | Weather Knows What Will Occur: Urban Public Nuisance Events Prediction and Control with Meteorological Assistance Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Predicting and controlling these nuisances is crucial but complicated due to their ties to subjective and psychological factors. In this study, we reveal a significant correlation between such nuisances and meteorological indicators, influenced by the impact of climate on people’s psychological states. |
Yi Xie; Tianyu Qiu; Yun Xiong; Xiuqi Huang; Xiaofeng Gao; Chao Chen; Qiang Wang; Haihong Li; |
| 530 | Microservice Root Cause Analysis With Limited Observability Through Intervention Recognition in The Latent Space Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The core idea is to infer the status of RCCs as latent variables with related monitoring metrics instead of directly extracting features from only the observable metrics. Based on this, we propose LatentScope, an unsupervised RCA framework with heterogeneous RCCs under limited observability. |
Zhe Xie; Shenglin Zhang; Yitong Geng; Yao Zhang; Minghua Ma; Xiaohui Nie; Zhenhe Yao; Longlong Xu; Yongqian Sun; Wentao Li; Dan Pei; |
| 531 | Understanding The Weakness of Large Language Model Agents Within A Complex Android Environment Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To address high-cost of manpower, we design a scalable and semi-automated method to construct the benchmark. |
Mingzhe Xing; Rongkai Zhang; Hui Xue; Qi Chen; Fan Yang; Zhen Xiao; |
| 532 | XRL-Bench: A Benchmark for Evaluating and Comparing Explainable Reinforcement Learning Techniques Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Despite their significant role, the lack of a unified evaluation framework hinders assessment of their accuracy and effectiveness. To address this, we introduce XRL-Bench, a unified standardized benchmark tailored for the evaluation and comparison of XRL methods, encompassing three main modules: standard RL environments, explainers based on state importance, and standard evaluators. |
Yu Xiong; Zhipeng Hu; Ye Huang; Runze Wu; Kai Guan; XingChen Fang; Ji Jiang; Tianze Zhou; YuJing Hu; Haoyu Liu; Tangjie Lyu; Changjie Fan; |
| 533 | Face4Rag: Factual Consistency Evaluation for Retrieval Augmented Generation in Chinese Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Without a comprehensive benchmark, it remains unexplored how these FCE methods perform on other LLMs with different error distributions or even unseen error types, as these methods may fail to detect the error types generated by other LLMs. To fill this gap, in this paper, we propose the first comprehensive FCE benchmark Face4RAG for RAG independent of the underlying LLM. |
Yunqi Xu; Tianchi Cai; Jiyan Jiang; Xierui Song; |
| 534 | Trinity: Syncretizing Multi-/Long-Tail/Long-Term Interests All in One Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel and unified framework in the retrieval stage, Trinity, to solve interest amnesia problem and improve multiple interest modeling tasks. |
Jing Yan; Liu Jiang; Jianfei Cui; Zhichen Zhao; Xingyan Bin; Feng Zhang; Zuotao Liu; |
| 535 | FedGTP: Exploiting Inter-Client Spatial Dependency in Federated Graph-based Traffic Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Existing studies have yet to address this non-trivial issue, thereby leading to sub-optimal performance. To fill this gap, we propose FedGTP, a new federated graph-based traffic prediction framework that promotes adaptive exploitation of inter-client spatial dependencies to recover close-to-optimal performance complying with privacy regulations like GDPR. |
Linghua Yang; Wantong Chen; Xiaoxi He; Shuyue Wei; Yi Xu; Zimu Zhou; Yongxin Tong; |
| 536 | Deep Ensemble Shape Calibration: Multi-Field Post-hoc Calibration in Online Advertising Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In terms of business understanding and interpretability, we decompose multi-field calibration into value calibration and shape calibration. We introduce innovative basis calibration functions, which enhance both function expression capabilities and data utilization by combining these basis calibration functions. |
Shuai Yang; Hao Yang; Zhuang Zou; Linhe Xu; Shuo Yuan; Yifan Zeng; |
| 537 | Enhancing Asymmetric Web Search Through Question-Answer Generation and Ranking Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper addresses the challenge of the semantic gap between user queries and web content, commonly referred to as asymmetric text matching, within the domain of web search. By leveraging BERT for reading comprehension, current algorithms enable significant advancements in query understanding, but still encounter limitations in effectively resolving the asymmetrical ranking problem due to model comprehension and summarization constraints.To tackle this issue, we propose the QAGR (Question-Answer Generation and Ranking) method, comprising an offline module called QAGeneration and an online module called QARanking. |
Dezhi Ye; Jie Liu; Jiabin Fan; Bowen Tian; Tianhua Zhou; Xiang Chen; Jin Ma; |
| 538 | OpenFedLLM: Training Large Language Models on Decentralized Private Data Via Federated Learning Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we offer a potential next step for contemporary LLMs: collaborative and privacy-preserving LLM training on the underutilized distributed private data via federated learning (FL), where multiple data owners collaboratively train a shared model without transmitting raw data. |
Rui Ye; Wenhao Wang; Jingyi Chai; Dihan Li; Zexi Li; Yinda Xu; Yaxin Du; Yanfeng Wang; Siheng Chen; |
| 539 | PAIL: Performance Based Adversarial Imitation Learning Engine for Carbon Neutral Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the problem, this study proposes a Performance based Adversarial Imitation Learning (PAIL) engine. |
Yuyang Ye; Lu-An Tang; Haoyu Wang; Runlong Yu; Wenchao Yu; Erhu He; Haifeng Chen; Hui Xiong; |
| 540 | SepsisLab: Early Sepsis Prediction with Uncertainty Quantification and Active Sensing Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this study, we first define such propagated uncertainty as the variance of prediction output and then introduce uncertainty propagation methods to quantify the propagated uncertainty. |
Changchang Yin; Pin-Yu Chen; Bingsheng Yao; Dakuo Wang; Jeffrey Caterino; Ping Zhang; |
| 541 | Unified Low-rank Compression Framework for Click-through Rate Prediction Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: Previous low-rank compression research mostly uses tensor decomposition, which can achieve a high parameter compression ratio, but brings in AUC degradation and additional computing overhead. To address these challenges, we propose a unified low-rank decomposition framework for compressing CTR prediction models. |
Hao Yu; Minghao Fu; Jiandong Ding; Yusheng Zhou; Jianxin Wu; |
| 542 | Unsupervised Ranking Ensemble Model for Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Unfortunately, the existing supervision is poorly designed, leading to serious information loss issue.To address this issue, we designed an unsupervised loss to compel the ranking ensemble model to learn all information of input rankings, including sequential and numerical information. |
Wenhui Yu; Bingqi Liu; Bin Xia; Xiaoxiao Xu; Ying Chen; Yongchang Li; Lantao Hu; |
| 543 | Pre-trained KPI Anomaly Detection Model Through Disentangled Transformer Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose KAD-Disformer, a KPI Anomaly Detection approach through Disentangled Transformer. |
Zhaoyang Yu; Changhua Pei; Xin Wang; Minghua Ma; Chetan Bansal; Saravan Rajmohan; Qingwei Lin; Dongmei Zhang; Xidao Wen; Jianhui Li; Gaogang Xie; Dan Pei; |
| 544 | An Offline Meta Black-box Optimization Framework for Adaptive Design of Urban Traffic Light Management Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we delve into two pivotal design components of the traffic light management system that can be dynamically adjusted to various traffic conditions: phase combination and phase time allocation. |
Taeyoung Yun; Kanghoon Lee; Sujin Yun; Ilmyung Kim; Won-Woo Jung; Min-Cheol Kwon; Kyujin Choi; Yoohyeon Lee; Jinkyoo Park; |
| 545 | OAG-Bench: A Human-Curated Benchmark for Academic Graph Mining Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this paper, we present OAG-Bench, a comprehensive, multi-aspect, and fine-grained human-curated benchmark based on the Open Academic Graph (OAG). |
Fanjin Zhang; Shijie Shi; Yifan Zhu; Bo Chen; Yukuo Cen; Jifan Yu; Yelin Chen; Lulu Wang; Qingfei Zhao; Yuqing Cheng; Tianyi Han; Yuwei An; Dan Zhang; Weng Lam Tam; Kun Cao; Yunhe Pang; Xinyu Guan; Huihui Yuan; Jian Song; Xiaoyan Li; Yuxiao Dong; Jie Tang; |
| 546 | A Self-boosted Framework for Calibrated Ranking Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: First, previous methods need to aggregate the full candidate list within a single mini-batch to compute the ranking loss. Such aggregation strategy violates extensive data shuffling which has long been proven beneficial for preventing overfitting, and thus degrades the training effectiveness. Second, existing multi-objective methods apply the two inherently conflicting loss functions on a single probabilistic prediction, which results in a sub-optimal trade-off between calibration and ranking.To tackle the two limitations, we propose a Self-Boosted framework for Calibrated Ranking (SBCR). |
Shunyu Zhang; Hu Liu; Wentian Bao; Enyun Yu; Yang Song; |
| 547 | D\'{o}lares or Dollars? Unraveling The Bilingual Prowess of Financial LLMs Between Spanish and English Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We construct a rigorously curated bilingual instruction dataset including over 144K Spanish and English samples from 15 datasets covering 7 tasks. Harnessing this, we introduce FinMA-ES, an LLM designed for bilingual financial applications. |
Xiao Zhang; Ruoyu Xiang; Chenhan Yuan; Duanyu Feng; Weiguang Han; Alejandro Lopez-Lira; Xiao-Yang Liu; Meikang Qiu; Sophia Ananiadou; Min Peng; Jimin Huang; Qianqian Xie; |
| 548 | Temporal Uplift Modeling for Online Marketing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, to tackle the aforementioned challenges, we present a temporal point process-based uplift model (TPPUM) that utilizes users’ temporal event sequences to estimate treatment effects via counterfactual analysis and temporal point processes. |
Xin Zhang; Kai Wang; Zengmao Wang; Bo Du; Shiwei Zhao; Runze Wu; Xudong Shen; Tangjie Lv; Changjie Fan; |
| 549 | Multi-Behavior Collaborative Filtering with Partial Order Graph Convolutional Networks Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To address the problem arising from the separate behavior graphs, we propose the concept of Partial Order Recommendation Graphs (POG). |
Yijie Zhang; Yuanchen Bei; Hao Chen; Qijie Shen; Zheng Yuan; Huan Gong; Senzhang Wang; Feiran Huang; Xiao Huang; |
| 550 | Large Language Model with Curriculum Reasoning for Visual Concept Recognition Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, realizing this goal is challenging given that i) the performance of symbolic representations are limited by the lack of annotated reasoning symbols and rules for most tasks, and ii) the LLMs may suffer from knowlege hallucination and dynamic open environment. To address these issues, in this paper, we propose CurLLM-Reasoner, a curriculum reasoning method based on symbolic reasoning and large language model for visual concept recognition. |
Yipeng Zhang; Xin Wang; Hong Chen; Jiapei Fan; Weigao Wen; Hui Xue; Hong Mei; Wenwu Zhu; |
| 551 | Optimizing Smartphone App Usage Prediction: A Click-Through Rate Ranking Approach Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, existing models often treat app usage prediction as a classification problem, which suffers from issues of app usage imbalance and out-of-distribution (OOD) during deployment. To address these challenges, this paper proposes a novel click-through rate (CTR) ranking-based method for predicting app usage. |
Yuqi Zhang; Meiying Kang; Xiucheng Li; Yu Qiu; Zhijun Li; |
| 552 | Unified Dual-Intent Translation for Joint Modeling of Search and Recommendation Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: But the joint modeling should deal with two problems: (1) accurately modeling users’ implicit demand intents in recommendation; (2) modeling the relation between the dual intents and the interactive items. To address these problems, we propose a novel model named Unified Dual-Intents Translation for joint modeling of Search and Recommendation (UDITSR). |
Yuting Zhang; Yiqing Wu; Ruidong Han; Ying Sun; Yongchun Zhu; Xiang Li; Wei Lin; Fuzhen Zhuang; Zhulin An; Yongjun Xu; |
| 553 | GraSS: Combining Graph Neural Networks with Expert Knowledge for SAT Solver Selection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present GraSS, a novel approach for automatic SAT solver selection based on tripartite graph representations of instances and a heterogeneous graph neural network (GNN) model. |
Zhanguang Zhang; Didier Ch\'{e}telat; Joseph Cotnareanu; Amur Ghose; Wenyi Xiao; Hui-Ling Zhen; Yingxue Zhang; Jianye Hao; Mark Coates; Mingxuan Yuan; |
| 554 | Diet-ODIN: A Novel Framework for Opioid Misuse Detection with Interpretable Dietary Patterns Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: To further delve into the intricate correlations between dietary patterns and opioid misuse, we exploit an LLM by utilizing the knowledge obtained from the graph learning model for interpretation. |
Zheyuan Zhang; Zehong Wang; Shifu Hou; Evan Hall; Landon Bachman; Jasmine White; Vincent Galassi; Nitesh V. Chawla; Chuxu Zha; Yanfang Ye; |
| 555 | TACCO: Task-guided Co-clustering of Clinical Concepts and Patient Visits for Disease Subtyping Based on EHR Data Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In this work, we introduce TACCO, a novel framework that jointly discovers clusters of clinical concepts and patient visits based on a hypergraph modeling of EHR data. |
Ziyang Zhang; Hejie Cui; Ran Xu; Yuzhang Xie; Joyce C. Ho; Carl Yang; |
| 556 | DUE: Dynamic Uncertainty-Aware Explanation Supervision Via 3D Imputation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Challenges associated with supervising visual explanations in the presence of an additional dimension include: 1) spatial correlation changed, 2) lack of direct 3D annotations, and 3) uncertainty varies across different parts of the explanation. To address these challenges, we propose a Dynamic Uncertainty-aware Explanation supervision (DUEfootnoteCode available at: https://github.com/AlexQilong/DUE.) |
Qilong Zhao; Yifei Zhang; Mengdan Zhu; Siyi Gu; Yuyang Gao; Xiaofeng Yang; Liang Zhao; |
| 557 | Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: In the traditional inference process, each token is generated sequentially by the LLM, leading to a time consumption proportional to the number of generated tokens. To enhance this process, our framework, named lookahead, introduces a multi-branch strategy. |
Yao Zhao; Zhitian Xie; Chen Liang; Chenyi Zhuang; Jinjie Gu; |
| 558 | GraphStorm: All-in-one Graph Machine Learning Framework for Industry Applications Related Papers Related Patents Related Grants Related Venues Related Experts Related Code View Highlight: We developed GraphStorm, which provides an end-to-end solution for scalable graph construction, graph model training and inference. |
Da Zheng; Xiang Song; Qi Zhu; Jian Zhang; Theodore Vasiloudis; Runjie Ma; Houyu Zhang; Zichen Wang; Soji Adeshina; Israt Nisa; Alejandro Mottini; Qingjun Cui; Huzefa Rangwala; Belinda Zeng; Christos Faloutsos; George Karypis; |
| 559 | Decision Focused Causal Learning for Direct Counterfactual Marketing Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Firstly, the budget allocation problem in marketing is a 0-1 integer stochastic programming problem and the budget is uncertain and fluctuates a lot in real-world settings, which is beyond the general problem background in DFL. Secondly, the counterfactual in marketing causes that the decision loss cannot be directly computed and the optimal solution can never be obtained, both of which disable the common gradient-estimation approaches in DFL. Thirdly, the OR solver is called frequently to compute the decision loss during model training in DFL, which produces huge computational cost and cannot support large-scale training data. In this paper, we propose a decision focused causal learning framework (DFCL) for direct counterfactual marketing optimization, which overcomes the above technological challenges. |
Hao Zhou; Rongxiao Huang; Shaoming Li; Guibin Jiang; Jiaqi Zheng; Bing Cheng; Wei Lin; |
| 560 | STATE: A Robust ATE Estimator of Heavy-Tailed Metrics for Variance Reduction in Online Controlled Experiments Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we develop a novel framework that integrates the Student’s t-distribution with machine learning tools to fit heavy-tailed metrics and construct a robust average treatment effect estimator in online controlled experiments, which we call STATE. |
Hao Zhou; Kun Sun; Shaoming Li; Yangfeng Fan; Guibin Jiang; Jiaqi Zheng; Tao Li; |
| 561 | Bringing Multimodality to Amazon Visual Search System Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we show that pure image-to- image matching suffers from false positives caused by matching to local visual patterns. |
Xinliang Zhu; Sheng-Wei Huang; Han Ding; Jinyu Yang; Kelvin Chen; Tao Zhou; Tal Neiman; Ouye Xie; Son Tran; Benjamin Yao; Douglas Gray; Anuj Bindal; Arnab Dhua; |
| 562 | Inductive Modeling for Realtime Cold Start Recommendations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To overcome the two challenges, we propose a novel architecture, the Item History Model (IHM). |
Chandler Zuo; Jonathan Castaldo; Hanqing Zhu; Haoyu Zhang; Ji Liu; Yangpeng Ou; Xiao Kong; |