AI RESEARCH
FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients
arXiv CS.AI
•
ArXi:2603.19722v1 Announce Type: cross Federated learning (FL) suffers from performance degradation due to the inevitable presence of noisy annotations in distributed scenarios. Existing approaches have advanced in distinguishing noisy samples from the dataset for label correction by leveraging loss values. However, noisy samples recognition relying on scalar loss lacks reliability for FL under heterogeneous scenarios.