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

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-02 04:00

研究人员开发了一个名为 SafeSubspace Pseudo-Label Refinement (S$^2$PLR) 的新框架，以提高 AI 模型在无源图域适应中的准确性。该方法通过识别一个 AI

排序理由 [lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Yingxu Wang, Xinwang Liu, Siyang Gao, Nan Yin · 2026-06-02 04:00

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

arXiv:2606.00808v1 Announce Type: new Abstract: 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 topolog…