Abstract:Graph foundation models (GFMs) seek transferable representations across graph domains but are limited by structural heterogeneity and incompatible node feature spaces. We propose Structure-Centric Graph Foundation Models (SCGFM), which treat graph topology as the primary source of transferable knowledge. Modeling graphs as metric measure spaces, SCGFM introduces learnable geometric bases that define a shared structural coordinate system. Graphs are aligned to these bases via Gromov-Wasserstein distances, yielding structure-aligned latent representations that accommodate heterogeneous graph topologies. To address feature incompatibility, SCGFM employs a structure-aware feature re-encoding mechanism that unifies node representations without assuming a fixed feature dimensionality or requiring dataset-specific preprocessing. Experiments on graph- and node-level tasks demonstrate strong in-domain and cross-domain generalization, outperforming existing GFM approaches.
| Comments: | Accepted by ICML 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Social and Information Networks (cs.SI) |
| Cite as: | arXiv:2605.08689 [cs.LG] |
| (or arXiv:2605.08689v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08689 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhao Kang [view email]
[v1]
Sat, 9 May 2026 04:56:21 UTC (904 KB)