Structure-Centric Graph Foundation Model via Geometric Bases
For graph machine learning practitioners, SCGFM provides a unified framework to handle structural heterogeneity and feature incompatibility across datasets, achieving strong cross-domain generalization.
SCGFM introduces learnable geometric bases to align diverse graph topologies via Gromov-Wasserstein distances, enabling transferable representations across domains. It outperforms existing graph foundation models on graph- and node-level tasks.
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.