AI RESEARCH
Structure-Centric Graph Foundation Model via Geometric Bases
arXiv CS.AI
•
ArXi:2605.08689v1 Announce Type: cross 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