<ul><li>The Graph Foundation Model (GFM) aims to provide a unified model for graph learning across different graphs and tasks.</li><li>A novel framework called H$^2$GFM has been introduced to generalize across both homogeneous TAGs (HoTAGs) and heterogeneous TAGs (HeTAGs).</li><li>H$^2$GFM uses a context-adaptive graph transformer (CGT) to capture information from context neighbors and their relationships for robust node representations.</li><li>Experiments on various types of text-attributed graphs show that H$^2$GFM is effective in capturing structural patterns among different graph types.</li></ul>

H$^2$GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs

Discover more