Multi-Source Wasserstein Distributionally Robust Graph Learning
This work proposes MS-WDRO, a multi-source Wasserstein distributionally robust graph learning framework that fuses heterogeneous sources via their weighted Wasserstein barycenter, a geometrically principled nominal distribution, then builds an ambiguity ball around it to hedge residual uncertainty.
Chuan-Sen Peng, Yifan Xia, Jinshan Zhong et al.
· 0 citations