7 papers
Toward General and Robust LLM-enhanced Text-attributed Graph Learning
Zihao Zhang, Xunkai Li, Rong-Hua Li +3
Recent advancements in Large Language Models (LLMs) and the proliferation of Text-Attributed Graphs (TAGs) across various domains have positioned LLM-enhanced TAG learning as a cri…
When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach
Zhihan Zhang, Xunkai Li, Yilong Zuo +5
Text-attributed graphs (TAGs) have become a key form of graph-structured data in modern data management and analytics, combining structural relationships with rich textual semantic…
Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs
Bowen Fan, Zhilin Guo, Xunkai Li +5
Graph Neural Networks (GNNs) have become a pivotal framework for modeling graph-structured data, enabling a wide range of applications from social network analysis to molecular che…
MagicDock: Toward Docking-oriented De Novo Ligand Design via Gradient Inversion
Zekai Chen, Xunkai Li, Sirui Zhang +6
De novo ligand design is a fundamental task that seeks to generate protein or molecule candidates that can effectively dock with protein receptors and achieve strong binding affini…
Two Facets of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models
Xunkai Li, Daohan Su, Sicheng Liu +5
Inspired by the success of LLMs, GFMs are designed to learn the optimal embedding functions from multi-domain text-attributed graphs for the downstream cross-task generalization ca…
DiRW: Path-Aware Digraph Learning for Heterophily
Daohan Su, Xunkai Li, Zhenjun Li +3
Recently, graph neural network (GNN) has emerged as a powerful representation learning tool for graph-structured data. However, most approaches are tailored for undirected graphs,…