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
Fragile Earth: Innovative AI For Climate Risk Mitigation
FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification
From Expansion to Retraction: Long-tailed Machine Unlearning via Boundary Manipulation
From Missteps to Mastery: Enhancing Low-Resource Dense Retrieval through Adaptive Query Generation
From Swath to Full-Disc: Advancing Precipitation Retrieval with Multimodal Knowledge Expansion
FRT: Flow-based Reconcile Transformer for Hierarchical Time Series
FULTR: A Large-Scale Fusion Learning to Rank Dataset and Its Application for Satisfaction-Oriented Ranking
FusionSAM: Visual Multi-Modal Learning with Segment Anything Model
Future Matters for Present: Towards Effective Physical Simulation over Meshes
FuzzyLight: A Robust Two-Stage Fuzzy Approach for Traffic Signal Control Works in Real Cities
GAS: Large-Scale Heterogeneous Personalization in Social Network Applications at Meta
GCoT: Chain-of-Thought Prompt Learning for Graphs
GDendrite: On Heterophilous Graph Contexts Mining with Versatile Neural Dendrites Framework
Generalizable Graph Prompt Learning Framework with Model-level Prompt Injection and Two-Stage Prompt Tuning
Generalizable Recommender System During Temporal Popularity Distribution Shifts
Generalizing Personalized Federated Graph Augmentation via Min-max Adversarial Learning
Generating by Understanding: Neural Visual Generation with Logical Symbol Groundings
Generating Long Semantic IDs in Parallel for Recommendation
Generative Imputation with Multi-level Causal Consistency for Variable Subset Forecasting
Generative Next POI Recommendation with Semantic ID
Generative Retrieval for Book Search
Generative Thinking, Corrective Action: User-Friendly Composed Image Retrieval via Automatic Multi-Agent Collaboration
Geometric view of soft decorrelation in self-supervised learning
GiGL: Large-Scale Graph Neural Networks at Snapchat
GLINT-RU: Gated Lightweight Intelligent Recurrent Units for Sequential Recommender Systems
Global Interpretable Graph-level Anomaly Detection via Prototype
GNN-SKAN: Advancing Molecular Representation Learning with SwallowKAN
GORACS: Group-level Optimal Transport-guided Coreset Selection for LLM-based Recommender Systems
GPE: Global Position Embedding for Trajectory Similarity Computation
Gradients as An Action: Towards Communication-Efficient Federated Recommender Systems via Adaptive Action Sharing
GRAND : Graph Reconstruction from Potential Partial Adjacency and Neighborhood Data
Graph Contrastive Learning with Progressive Augmentations
Graph Evidential Learning for Anomaly Detection
Graph Foundation Models: Challenges, Methods, and Open Questions
GraphLAMA: Enabling Efficient Adaptation of Graph Language Models with Limited Annotations
Graph Learning with Distributional Edge Layouts
GraphLoRA: Structure-Aware Contrastive Low-Rank Adaptation for Cross-Graph Transfer Learning
Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networks
Graph Positional Autoencoders as Self-supervised Learners
Graph Prompting for Graph Learning Models: Recent Advances and Future Directions
GraphTool-Instruction: Revolutionizing Graph Reasoning in LLMs through Decomposed Subtask Instruction
Graph Triple Attention Networks: A Decoupled Perspective
GRASP: Differentially Private Graph Reconstruction Defense with Structured Perturbation
GREAT: Guiding Query Generation with a Trie for Recommending Related Search about Video at Kuaishou
Grid and Road Expressions Are Complementary for Trajectory Representation Learning
GROOT: Effective Design of Biological Sequences with Limited Experimental Data
GuARD: Effective Anomaly Detection through a Text-Rich and Graph-Informed Language Model
Handling Feature Heterogeneity with Learnable Graph Patches
Harnessing Influence Function in Explaining Graph Neural Networks
Harnessing Scale and Physics: A Multi-Graph Neural Operator Framework for PDEs on Arbitrary Geometries

« prev Page 7/15 next »