3 papers
cs.LG2026
What Makes Graph Unified? Principles and Generative Sliding-Window Transformer for Graph Foundation Models
Dongxiao He, Siqi Liu, Jitao Zhao +3
Graph Foundation Models (GFMs) have recently emerged as a promising paradigm for general-purpose graph learning, aiming to learn reusable knowledge that generalizes across diverse…
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.LG2025
One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
Yongqi Huang, Jitao Zhao, Dongxiao He +5
Graph Prompt Learning (GPL) has emerged as a promising paradigm that bridges graph pretraining models and downstream scenarios, mitigating label dependency and the misalignment bet…