OmniSage: Large Scale, Multi-Entity Heterogeneous Graph Representation Learning
机构 * Pinterest
Comments To appear in Proceedings of KDD 2025 Industry Track
期刊&会议
KDD
ACM SIGKDD Conference on Knowledge Discovery and Data Mining · 会议 · Data Mining
Efficient Heuristics Generation for Solving Combinatorial Optimization Problems Using Large Language Models
Comments Accepted by SIGKDD 2025
Lost in Sequence: Do Large Language Models Understand Sequential Recommendation?
机构 * NAVER Corperation（NAVER公司） ； University of California San Diego（加州大学圣地亚哥分校）
Comments KDD 2025 Research Track
Bias Detection via Maximum Subgroup Discrepancy
机构 * Czech Technical University in Prague, Faculty of Electrical Engineering（捷克技术大学布拉格电子工程学院）
Comments 12 pages, 6 figures
Journal ref Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (2025)
Paths to Causality: Finding Informative Subgraphs Within Knowledge Graphs for Knowledge-Based Causal Discovery
机构 * Fujitsu Limited（富士通有限公司）
Comments Accepted at KDD 2025 (full research paper)
Graph Prompting for Graph Learning Models: Recent Advances and Future Directions
机构 * University of Virginia（弗吉尼亚大学） ； University of Notre Dame（诺丁汉大学） ； University of Connecticut（康涅狄格大学）
Comments Accepted by KDD 2025 Tutorial/Survey Track
Fair Diversity Maximization with Few Representatives
Comments To appear in KDD 2025
Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval
机构 * Queen's University（皇后大学） ； Amazon（亚马逊）
Comments KDD '25
Addressing Correlated Latent Exogenous Variables in Debiased Recommender Systems
机构 * Dalhousie University（达尔豪斯大学） ； Beijing University of Chemical Technology（北京化工大学） ； University of Michigan（密歇根大学）
Comments In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD '25), August 3--7, 2025, Toronto, ON, Canada
Predicting the Dynamics of Complex System via Multiscale Diffusion Autoencoder
Comments KDD 2025
One Fits All: Learning Fair Graph Neural Networks for Various Sensitive Attributes
机构 * Sun Yat-sen University（中山大学） ； Tencent AI Lab（腾讯AI实验室）
Comments Published in KDD 2024
Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models
机构 * Tsinghua Univerisity（清华大学） ； Peking University（北京大学） ； Hong Kong University of Science and Technology（香港理工大学） ； Beihang Univerisity（北京航空航天大学）
Comments Accepted by KDD 2025 research track
Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection
机构 * Ubisoft La Forge（育碧La Forge） ； McGill University（麦吉尔大学） ； Mila ； CIFAR AI Chair（CIFAR人工智能主席）
Comments 11 pages, 1 figure, 9 Tables, KDD 2025 ADS Track
Fast Causal Discovery by Approximate Kernel-based Generalized Score Functions with Linear Computational Complexity
机构 * Fudan University（复旦大学） ； SIAT, Chinese Academy of Sciences（中国科学院深圳先进技术研究院） ； Tongji University（同济大学）
Journal ref 2025. Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1. Association for Computing Machinery, New York, NY, USA
Optimizing Recall or Relevance? A Multi-Task Multi-Head Approach for Item-to-Item Retrieval in Recommendation
Journal ref KDD 2025
Synthetic Tabular Data: Methods, Attacks and Defenses
机构 * Meta and University of Warwick（Meta 和 战略研究学院）
Comments Survey paper for accepted lecture-style tutorial at ACM KDD 2025
LaDEEP: A Deep Learning-based Surrogate Model for Large Deformation of Elastic-Plastic Solids
机构 * Peking University School of Computer Science（北京大学计算机科学学院） ； University of Southampton School of Electrical and Computer Science（南安普顿大学电子与计算机科学学院）
Comments Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD '25)
NILMFormer: Non-Intrusive Load Monitoring that Accounts for Non-Stationarity
机构 * EDF R&D - Université Paris Cité（EDF研究与开发 - 巴黎大学）
Comments 12 pages, 8 figures. This paper appeared in ACM SIGKDD 2025
Journal ref In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD '25), August 3--7, 2025, Toronto, ON, Canada
Generating Long Semantic IDs in Parallel for Recommendation
Comments KDD 2025
Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning
机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（认知智能国家重点实验室，中国科学技术大学） ； Research Center for Social Computing and Interactive Robotics, Harbin Institute of Technology（社会计算与交互机器人研究中心，哈尔滨工业大学）
Comments Accepted at the Research Track of KDD 2025
Unleashing The Power of Pre-Trained Language Models for Irregularly Sampled Time Series
机构 * HKUST(GZ)（香港科技大学（广州））
Comments Accepted by KDD'25
Generating by Understanding: Neural Visual Generation with Logical Symbol Groundings
机构 * State Key Laboratory of CAD&CG（CAD与CG国家重点实验室） ； National Key Laboratory for Novel Software Technology（新型软件技术国家实验室） ； Department of Computer and Information Science（计算机与信息科学系）
Comments KDD 2025 research track paper
FlexiReg: Flexible Urban Region Representation Learning
机构 * School of Computing and Information System, University of Melbourne（计算与信息系统学院，墨尔本大学）
Comments This paper is accepted at KDD 2025
SDE: A Simplified and Disentangled Dependency Encoding Framework for State Space Models in Time Series Forecasting
机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港理工大学（广州）） ； The Hong Kong University of Science and Technology（香港理工大学）
Comments Accepted by KDD 2025
When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmark
机构 * Massachusetts Institute of Technology（麻省理工学院） ； IBM Research（IBM研究院） ； Virginia Tech（弗吉尼亚理工大学）
Comments This work has been accepted to the KDD 2025 Datasets and Benchmarks Track
TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest
Comments \c{opyright} {ACM} {2023}. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in KDD'23, http://dx.doi.org/10.1145/3580305.3599918
Bypassing Skip-Gram Negative Sampling: Dimension Regularization as a More Efficient Alternative for Graph Embeddings
机构 * Northeastern University（东北大学） ； Khoury College of Computer Sciences（计算机科学学院） ； Amazon AWS（亚马逊AWS） ； San Francisco CA USA（旧金山CA美国） ； Network Science Institute（网络科学研究所） ； Stanford University（斯坦福大学） ； Management Science & Engineering（管理科学与工程） ； Stanford CA USA（斯坦福CA美国）
Comments Published in KDD'25
A Diffusion-Based Method for Learning the Multi-Outcome Distribution of Medical Treatments
机构 * Munich Center for Machine Learning & LMU Munich（慕尼黑机器学习中心及慕尼黑大学） ； University of Illinois, Chicago（伊利诺伊大学香槟分校）
Comments Accepted at KDD 2025
TimeGraph: Synthetic Benchmark Datasets for Robust Time-Series Causal Discovery
机构 * Causal AI Lab University of Maryland, Baltimore County（因果AI实验室 乌尔利卡大学巴尔的摩县）
Comments 11 pages, 4 figures, accepted at KDD 2025 (Datasets and Benchmarks Track)
Boosting Bot Detection via Heterophily-Aware Representation Learning and Prototype-Guided Cluster Discovery
机构 * University of Science and Technology of China（中国科学技术大学）
Comments KDD 2025
