activity
20242026
collaborators
Showing 2025Show all

5 papers · 1 filter

cs.LG2025

Knowledge-Driven Federated Graph Learning on Model Heterogeneity

Zhengyu Wu, Guang Zeng, Huilin Lai +7

Federated graph learning (FGL) has emerged as a promising paradigm for collaborative graph representation learning, enabling multiple parties to jointly train models while preservi…

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,…

cs.LG2025

Towards Unbiased Federated Graph Learning: Label and Topology Perspectives

Zhengyu Wu, Boyang Pang, Xunkai Li +6

Federated Graph Learning (FGL) enables privacy-preserving, distributed training of graph neural networks without sharing raw data. Among its approaches, subgraph-FL has become the…

cs.LG2025

Toward Effective Digraph Representation Learning: A Magnetic Adaptive Propagation based Approach

Xunkai Li, Daohan Su, Zhengyu Wu +4

The -parameterized magnetic Laplacian serves as the foundation of directed graph (digraph) convolution, enabling this kind of digraph neural network (MagDG) to encode node featu…