ICDE 2025
288 papers
The 2025 ICDE conference featured 376 papers covering a range of data engineering and management topics. Research themes focused on temporal and spatio-temporal analysis, including multi-scale temporal convolutions for time series and dynamic graph learning for urban forecasting. Multi-view learning also represented a primary research direction, specifically regarding adaptive weighting and consensus graph learning for data fusion.
Privacy and security were addressed through work on local differential privacy for truss decomposition and secure similarity computation for encrypted vector search. Graph analytics remained a central topic, covering space-efficient representations and the application of AI-generated content (AIGC) to graph structures. Other research explored online scheduling for continuous queries and shortest path counting on road networks. Prolific contributors to this edition included Yunjun Gao, Jianliang Xu, Ying Zhang, and Xiaofang Zhou.
Top Research Directions
Research directions most represented by ICDE 2025 papers.
Top Authors
Impactful Papers
Papers from ICDE 2025 that shaped research clusters.
Influential
Towards Robustness of Text-to-Visualization Translation Against Lexical and Phrasal Variability
influential
Grounding Language Models with External
Efficient Methods for Accurate Sparse Trajectory Recovery and Map Matching
influential
Modeling Road Network Topology for Auton
Towards Fair Graph Neural Networks via Graph Counterfactual Without Sensitive Attributes
influential
Dynamic Subgroup Weighting for Equitable
Data Driven Decision Making with Time Series and Spatio-temporal Data
influential
Cross-Domain Generalization for Spatio-T
DaRec: A Disentangled Alignment Framework for Large Language Model and Recommender System
influential
Disentangling Shared and Specific Featur