#machine learning
Sep 2026
Graph Domain Adaptation Does Not End with Representation Learning
EviGDA is proposed, an Evidence-Augmented Graph Domain Adaptation framework that complements graph representation adaptation with a graph-free local expert, and shows that EviGDA outperforms state-of-the-art baselines.
Zi-Qian Liu, Yong-Xue Xu, En-Ze Zhang et al.
· arXiv.org · 0 citations