AI RESEARCH
A Graph Foundation Model with Spectral Parsing and Prototype-Guided Spatial Propagation
arXiv CS.LG
•
ArXi:2606.03315v1 Announce Type: new Graph foundation models aim to learn transferable knowledge from diverse graphs for generalization to unseen graphs and tasks. Unlike text and images, graphs lack a shared vocabulary or regular spatial grid, making cross-graph transfer challenging. This challenge comes from both feature discrepancies and, critically, diverse graph structures. Existing GFMs mainly improve transferability by unifying feature spaces or incorporating structural tokens and vocabularies. However, existing topology-aware designs still have limitations.