Learning Graph Foundation Models on Riemannian Graph-of-Graphs
For graph machine learning practitioners, this work addresses the scale mismatch problem in graph foundation models, enabling better generalization across diverse tasks.
Existing graph foundation models suffer from scale mismatch due to fixed-hop subgraph sampling. R-GFM introduces a Riemannian Graph-of-Graphs approach that treats structural scale as a first-class citizen, achieving up to 49% relative improvement on downstream tasks.
Graph foundation models (GFMs), pretrained on massive graph data, have transformed graph machine learning by supporting 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. R-GFM constructs a multi-scale GoG over-sampled subgraphs at different hop distances and learns geometry-adaptive representations from Riemannian manifolds. Theoretical analysis shows that R-GFM reduces structural domain generalization error compared to fixed-scale GFMs. Experiments on various datasets demonstrate that R-GFM achieves state-of-the-art performance, with up to a 49% relative improvement on downstream tasks. Our code is available at https://github.com/USTC-DataDarknessLab/R-GFM.