AI RESEARCH
Scaling Unsupervised Multi-Source Federated Domain Adaptation through Group-Wise Discrepancy Minimization
arXiv CS.LG
•
ArXi:2510.08150v3 Announce Type: replace Unsupervised multi-source domain adaptation (UMDA) leverages labeled data from multiple source domains to generalize to an unlabeled target. While federated UMDA addresses privacy by avoiding raw data sharing, existing methods scale poorly as the number of sources increases, often suffering from high computational overhead or