AI RESEARCH

Safe-Subspace Pseudo-Label Refinement for Source-Free Graph Domain Adaptation

arXiv CS.LG

ArXi:2606.00808v1 Announce Type: new Source-free graph domain adaptation (SF-GDA) aims to adapt source-trained graph models to unlabeled target graphs when source graphs are no longer accessible. A central obstacle is pseudo-label reliability: under feature and topological shifts, source-induced predictions may become confidently wrong, and indiscriminate self-