AI RESEARCH

CrossHGL: A Text-Free Foundation Model for Cross-Domain Heterogeneous Graph Learning

arXiv CS.LG

ArXi:2603.27685v1 Announce Type: new Heterogeneous graph representation learning (HGRL) is essential for modeling complex systems with diverse node and edge types. However, most existing methods are limited to closed-world settings with shared schemas and feature spaces, hindering cross-domain generalization. While recent graph foundation models improve transferability, they often target homogeneous graphs, rely on domain-specific schemas, or require rich textual attributes. Consequently, text-free and few-shot cross-domain HGRL remains underexplored.