KDD 2025

749 papers

Top Research Directions

Research directions most represented by KDD 2025 papers.

Dynamic Preference Modeling in Interactive Systems 18
Overcoming the Homophily Assumption in Graph Neural Networks 12
Mitigating Popularity Bias in Recommender Systems 10
Incremental Maintenance of Dynamic Graph Indices 10
Fusing Semantic and Structural Representations on Textual Graphs 7
Why General Language Models Fail at Expert Tasks 7
Zero Shot Generalization in Time Series Foundation Models 6
Adapting Homogeneous Graph Learning to Heterogeneous Structures 6
Over-Smoothing in Graph Neural Networks 6
Iterative Retrieval Augmented Generation for Multi Hop Reasoning 5
Bridging Feature Space Misalignment in Cross-Domain Graph Learning 5
Aligning Feature and Topological Shifts in Graph Neural Networks 5
Self Supervised Regularization for Sparse Recommender Systems 5
Mitigating the Cold Start Problem in Recommender Systems 5
Latent Space Alignment for Cold Start Recommendation 5

Top Authors

AuthorPapers
Xiangyu Zhao10
Carl Yang9
Fan Wu9
Hui Xiong9
Bo Zheng8
Dawei Yin8
Hao Liu8
Yong Li8
Julian McAuley7
Yuxuan Liang7
Zhenzhe Zheng7
Bin Yang6
Chuan Shi6
Defu Lian6
Jian Xu6
Jiliang Tang6
Shuaiqiang Wang6
Dawei Zhou5
Haoxuan Li5
Hongzhi Yin5

Impactful Papers

Papers from KDD 2025 that shaped research clusters.

Foundational

Influential

Papers

Title
Combining Denoised Neural Network and Genetic Symbolic Regression for Memory Behavior Modeling via Dynamic Asynchronous Optimization
CompanyKG2: A Large-Scale Heterogeneous Graph for Company Similarity Quantification
CompilerDream: Learning a Compiler World Model for General Code Optimization
Complicated Semantic Alignment for Long-Tail Query Rewriting in Taobao Search Based on Large Language Model
CompressGNN: Accelerating Graph Neural Network Training via Hierarchical Compression
Compressive Meta-Learning
ComRecycle: An Intelligent Computation Recycling Framework for Online Advertising
ConciseExplain: Reducing Redundancy and Spuriousness in Persuasive Recommendation Explanation
Conditional Generative Modeling for High-dimensional Marked Temporal Point Processes
Connecting Domains and Contrasting Samples: A Ladder for Domain Generalization
Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction
Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs
Contextual Generative Auction with Permutation-level Externalities for Online Advertising
Continuous Optimization for Feature Selection with Permutation-Invariant Embedding and Policy-Guided Search
Contrastive Graph Condensation: Advancing Data Versatility through Self-Supervised Learning
Contrastive Text-enhanced Transformer for Cross-Domain Sequential Recommendation
CoopRide: Cooperate All Grids in City-Scale Ride-Hailing Dispatching with Multi-Agent Reinforcement Learning
Correlation-Aware Graph Convolutional Networks for Multi-Label Node Classification
Counterfactual Fairness Through Transforming Data Orthogonal to Bias
CovDocker: Benchmarking Covalent Drug Design with Tasks, Datasets, and Solutions
Covering Cracks in Content Moderation: Delexicalized Distant Supervision for Illicit Drug Jargon Detection
CrossLinear: Plug-and-Play Cross-Correlation Embedding for Time Series Forecasting with Exogenous Variables
Cross-Species Insights: Transforming Drug Efficacy from Rats to Humans Using Tissue-Specific Generative Models
Cross-Validation for Longitudinal Datasets with Unstable Correlations
CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies
Cuff-KT: Tackling Learners' Real-time Learning Pattern Adjustment via Tuning-Free Knowledge State Guided Model Updating
CURE: A dataset for Clinical Understanding & Retrieval Evaluation
DarkDistill: Difficulty-Aligned Federated Early-Exit Network Training on Heterogeneous Devices
Data Glitches Discovery using Influence-based Model Explanations
Data Heterogeneity Modeling for Trustworthy Machine Learning
Data Watermarking for Sequential Recommender Systems
DCA-Bench: A Benchmark for Dataset Curation Agents
Decoupling Spatio-Temporal Prediction: When Lightweight Large Models Meet Adaptive Hypergraphs
Delving into Instance-Dependent Label Noise in Graph Data: A Comprehensive Study and Benchmark
Denoising Programming Knowledge Tracing with a Code Graph-based Tuning Adaptor
Depth-Adaptive Graph Neural Networks via Learnable Bakry-'Emery Curvature
Depth-Adaptive Graph Neural Networks via Learnable Bakry-Émery Curvature
Differentially Private Synthetic Data Release for Topics API Outputs
Diffmv: A Unified Diffusion Framework for Healthcare Predictions with Random Missing Views and View Laziness
Diffusion-Guided Diversity for Single Domain Generalization in Time Series Classification
Diffusion-Inspired Cold Start with Sufficient Prior in Computerized Adaptive Testing
Diffusion Models for Recommender Systems: From Content Distribution To Content Creation
Diffusion-Scheduled Denoising Autoencoders for Anomaly Detection in Tabular Data
DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi
DimCL: Dimension-Aware Augmentation in Contrastive Learning for Recommendation
DIPS: Optimal Dynamic Index for Poisson πps Sampling
DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models
Discrepancy-Aware Graph Mask Auto-Encoder
DistPred: A Distribution-Free Probabilistic Inference Method for Regression and Forecasting
Distributional Prototype Learning for Out-of-distribution Detection

« prev Page 4/15 next »