AI RESEARCH
VARS-FL: Validation-Aligned Client Selection for Non-IID Federated Learning in IoT Systems
arXiv CS.LG
•
ArXi:2605.05896v1 Announce Type: new Federated learning (FL) systems typically employ stateless client selection, treating each communication round independently and ignoring accumulated evidence of client contribution quality. Under non-IID data, this leads to slow convergence and unstable