Publications
-
GDGB: A Benchmark for Generative Dynamic Text-Attributed Graph Learning
Work in progress. -
Future Link Prediction Without Memory or Aggregation
In NeurIPS 2025. -
Exploring the Potential of Large Language Models as Predictors in Dynamic Text-Attributed Graphs
Work in progress. -
Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
In NeurIPS 2024. -
LLM-Based Multi-Agent Systems are Scalable Graph Generative Models
In ACL (Findings) 2024. -
Beyond Over-smoothing: Uncovering the Trainability Challenges in Deep Graph Neural Networks
In CIKM 2024. -
Scalable and Accurate Graph Reasoning with LLM-based Multi-Agents
Work in progress. -
Learning-based Property Estimation with Polynomials
In SIGMOD 2024. -
PolyGCL: Graph Contrastive Learning via Learnable Spectral Polynomial Filters
In ICLR 2024. -
Evennet: Ignoring odd-hop neighbors improves robustness of graph neural networks
In NeurIPS 2022.