Abstract: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 this https URL.
| Comments: | This paper has been accepted by ICML 2026 |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.09993 [cs.LG] |
| (or arXiv:2605.09993v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.09993 arXiv-issued DOI via DataCite (pending registration) |
From: Zezhong Ding [view email]
[v1]
Mon, 11 May 2026 05:09:16 UTC (762 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。