AI RESEARCH
Empowering Heterogeneous Graph Foundation Models via Decoupled Relation Alignment
arXiv CS.AI
•
ArXi:2605.00731v1 Announce Type: cross While Graph Foundation Models (GFMs) have achieved remarkable success in homogeneous graphs, extending them to multi-domain heterogeneous graphs (MDHGs) remains a formidable challenge due to cross-type feature shifts and intra-domain relation gaps. Existing global feature alignment methods (PCA or SVD) enforce a shared feature space blindly, which distorts type-specific semantics and disrupts original topologies, inevitably leading to "Type Collapse" and "Relation Confusion.