AI RESEARCH
Learning Graph Foundation Models on Riemannian Graph-of-Graphs
arXiv CS.LG
•
ArXi:2605.09993v1 Announce Type: new Graph foundation models (GFMs), pretrained on massive graph data, have transformed graph machine learning by ing general-purpose reasoning across diverse graph tasks and domains. Existing GFMs pretrained with fixed-hop subgraph sampling impose a fixed receptive field, causing scale mismatch on diverse tasks, which often require heterogeneous and unknown structural contexts beyond a fixed sampling scale. We propose R-GFM, a Riemannian Graph-of-Graphs (GoG) based foundation model, that treats structural scale as a first-class citizen in modeling.