1 citations · 1 across the 4 of their papers we have counts for
4 papers
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…
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…
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…
Spatial-Temporal Adaptive Graph Convolution with Attention Network for Traffic Forecasting
Chen Weikang, Li Yawen, Xue Zhe +2
Traffic forecasting is one canonical example of spatial-temporal learning task in Intelligent Traffic System. Existing approaches capture spatial dependency with a pre-determined m…