collaborators

5 papers

cs.LG2026

CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts

Peiyuan Li, Yongqi Huang, Jitao Zhao +3

Heterogeneous Graph Prompt Learning (HGPL)has emerged as a promising paradigm for bridging the gap between the objectives of pre-training foundation models and their downstream app…

cs.LG2026

A Graph Foundation Model with Spectral Parsing and Prototype-Guided Spatial Propagation

Ankang Yang, Jitao Zhao, Dongxiao He +3

Graph foundation models aim to learn transferable knowledge from diverse graphs for generalization to unseen graphs and tasks. Unlike text and images, graphs lack a shared vocabula…

cs.LG2026

Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding

Chundong Liang, Yongqi Huang, Dongxiao He +4

Graph pre-training has achieved remarkable success in recent years, delivering transferable representations for downstream adaptation. However, most existing methods are designed f…

cs.LG2026

LEDA: Latent Semantic Distribution Alignment for Multi-domain Graph Pre-training

Lianze Shan, Jitao Zhao, Dongxiao He +3

Recent advances in generic large models, such as GPT and DeepSeek, have motivated the introduction of universality to graph pre-training, aiming to learn rich and generalizable kno…

cs.LG2026

MUG: Meta-path-aware Universal Heterogeneous Graph Pre-Training

Lianze Shan, Jitao Zhao, Dongxiao He +3

Universal graph pre-training has emerged as a key paradigm in graph representation learning, offering a promising way to train encoders to learn transferable representations from u…