Enhancing Homophily-Heterophily Separation: Relation-Aware Learning in Heterogeneous Graphs
机构 * School of Computer Science and Technology（计算机科学与技术学院） ； Xidian University（西安电子科技大学）
Comments accepted by KDD 2025
期刊&会议
KDD
ACM SIGKDD Conference on Knowledge Discovery and Data Mining · 会议 · Data Mining
MockLLM: A Multi-Agent Behavior Collaboration Framework for Online Job Seeking and Recruiting
机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； Engineering Research Center of Next-Generation Intelligent Search and Recommendation（下一代智能搜索与推荐工程研究中心） ； University of Chinese Academy of Sciences（中国科学院大学） ； Nanbeige Lab, BOSS Zhipin（Boss Zhipin纳米贝实验室） ； King Abdullah University of Science and Technology（卡布斯科学技术大学） ； School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）
Comments Accepted by KDD 2025 Research Track
Rewarding Graph Reasoning Process makes LLMs more Generalized Reasoners
机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））
Comments Accepted to KDD 2025 Research Track
Towards Better Benchmark Datasets for Inductive Knowledge Graph Completion
机构 * Michigan State University（密歇根州立大学）
Comments KDD'25 Datasets & Benchmark Track
An Audio-centric Multi-task Learning Framework for Streaming Ads Targeting on Spotify
Comments Accepted at KDD 2025
PERSCEN: Learning Personalized Interaction Pattern and Scenario Preference for Multi-Scenario Matching
机构 * School of Computer Science（计算机科学学院） ； Northwestern Polytechnical University（西北工业大学） ； Beijing Institute of Mathematical Sciences and Applications（北京数学科学应用研究所） ； Department of Electronic Engineering（电子工程系） ； Tsinghua University（清华大学） ； School of Cybersecurity（网络安全学院）
Comments Accepted by KDD 2025
LLMs for Customized Marketing Content Generation and Evaluation at Scale
机构 * Texas A\&M University（德克萨斯大学） ； Amazon Inc.（亚马逊公司）
Comments KDD LLM4ECommerce Workshop 2025
From Unstructured Communication to Intelligent RAG: Multi-Agent Automation for Supply Chain Knowledge Bases
机构 * Amazon Operational Technology Solutions（亚马逊运营技术解决方案）
Comments Accepted In Proceedings of the 1st Workshop on AI for Supply Chain: Today and Future @ 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD 25), August 3, 2025, Toronto, ON, Canada. ACM, New York, NY, USA, 14 pages, 2 figures
LaPuda: LLM-Enabled Policy-Based Query Optimizer for Multi-modal Data
机构 * University of Hawaii（夏威夷大学） ； University of Florida（佛罗里达大学）
Comments Yifan and Haodi contributed equally to the work, accepted by PAKDD 2025
Journal ref Advances in Knowledge Discovery and Data Mining. PAKDD 2025
Confidence Scoring for LLM-Generated SQL in Supply Chain Data Extraction
Comments accepted by KDD workshop AI for Supply Chain 2025
Pre-training Time Series Models with Stock Data Customization
Comments Accepted by KDD 2025
SIDE: Semantic ID Embedding for effective learning from sequences
机构 * Meta Platforms, Inc.（Meta平台）
Comments 7 pages, 4 images, 6 tables
Journal ref KDD workshop, 2025
Towards Efficient Few-shot Graph Neural Architecture Search via Partitioning Gradient Contribution
机构 * College of Software, Jilin University（吉林大学软件学院） ； College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院） ； Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University（教育部符号计算与知识工程重点实验室，吉林大学） ； School of Computer Science, Zhuhai College of Science and Technology（珠海科技学院计算机科学学院） ； College of Computer Science and Technology, Dalian University of Technology（大连理工大学计算机科学与技术学院） ； Department of Mechanical Engineering, National University of Singapore（新加坡国立大学机械工程系）
Comments Accepted by SIGKDD 2025
Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinement
机构 * School of Computational Science \& Engineering Georgia Institute of Technology Atlanta GA USA ； Scheller College of Business Georgia Institute of Technology Atlanta GA USA ； Georgia Institute of Technology
Comments Accepted at KDD'25
LiSA: Leveraging Link Recommender to Attack Graph Neural Networks via Subgraph Injection
机构 * Keio University（keio大学） ； Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Comments PAKDD 2025
Journal ref Pacific-Asia Conference on Knowledge Discovery and Data Mining 2025
HSTU-BLaIR: Lightweight Contrastive Text Embedding for Generative Recommender
机构 * Ming Hsieh Department of Electrical and Computer Engineering（电气与计算机工程系）
Comments Accepted at the Workshop on Large Language Models for E-Commerce, KDD 2025. Code available at https://www.github.com/snapfinger/HSTU-BLaIR
Generative Next POI Recommendation with Semantic ID
Comments 11 pages, 4 figures, the paper has been accepted by KDD 2025
Single-Agent vs. Multi-Agent LLM Strategies for Automated Student Reflection Assessment
机构 * Kyushu University, Fukuoka, Japan（九州大学） ； Nagoya University, Nagoya, Japan（名古屋大学） ； Chubu University, Kasugai, Japan（名古屋大学）
Comments Published in Proceedings of the 29th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2025), see https://doi.org/10.1007/978-981-96-8186-0_24
SatHealth: A Multimodal Public Health Dataset with Satellite-based Environmental Factors
机构 * The Ohio State University（俄亥俄州立大学）
Comments 18 pages, 6 figures. To be published in SIGKDD 2025 Datasets and Benchmarks Track
Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark
机构 * Pohang University of Science（光州科学技术大学） ； Korea University（韩国大学）
Comments 12 pages
Journal ref KDD 2025
GORACS: Group-level Optimal Transport-guided Coreset Selection for LLM-based Recommender Systems
Comments Accepted by KDD 2025
Merlin: Multi-View Representation Learning for Robust Multivariate Time Series Forecasting with Unfixed Missing Rates
机构 * Institute of Computing Technology, Chinese Academy of Sciences（计算技术研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学）
Comments Accepted by SIGKDD 2025 (Research Track)
Graph Positional Autoencoders as Self-supervised Learners
机构 * Beijing University of Posts and Telecommunications（北京邮电大学） ； National University of Singapore（新加坡国立大学） ； Singapore Management University（新加坡管理学院）
Comments 12 pages, 3 figures, Accepted at KDD 2025
TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks
机构 * New York University（纽约大学） ； New York University Shanghai（纽约大学上海）
Comments 12 pages, 5 figures, in KDD 2025
ScIRGen: Synthesize Realistic and Large-Scale RAG Dataset for Scientific Research
机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） ； Institute of Tibetan Plateau Research, Chinese Academy of Sciences（中国科学院青藏高原研究所） ； Lanzhou University（兰州大学） ； College of Resources and Environment, University of Chinese Academy of Sciences（中国科学院大学资源与环境学院）
Comments KDD 2025 Accepted
Enhancing Large Language Models for Mobility Analytics with Semantic Location Tokenization
机构 * Nanyang Technological University（南洋理工大学） ； Southern University of Science and Technology（南方科技大学）
Comments Accepted by KDD'25
Denoising Programming Knowledge Tracing with a Code Graph-based Tuning Adaptor
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） ； Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（人工智能研究院，合肥综合性国家科学中心）
Comments Accepted by KDD August 2025
A Survey on Deep Learning based Time Series Analysis with Frequency Transformation
机构 * State Information Center（信息中心） ； Tongji University（同济大学） ； University of Auckland（奥克兰大学） ； Macquarie University（麦考瑞大学） ； University of Technology Sydney（悉尼大学） ； Beijing Institute of Technology（北京理工大学） ； Hong Kong University of Science（香港科学大学）
Comments Accepted By KDD 2025
LightKG: Efficient Knowledge-Aware Recommendations with Simplified GNN Architecture
机构 * Zhejiang University（浙江大学） ； Singapore University of Technology and Design（新加坡技术与设计大学）
Comments Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining
"Check My Work?": Measuring Sycophancy in a Simulated Educational Context
机构 * USC Gould School of Law（USC 法学院）
Comments Presented at KDD Workshop on Ethical Artificial Intelligence: Methods and Applications (EAI) 2025
