collaborators

7 papers

cs.LG2026

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…

cs.LG2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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,…