AI RESEARCH
FedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation
arXiv CS.AI
•
ArXi:2603.27986v1 Announce Type: cross Federated learning (FL) enables distributed clients to collaboratively train a global model using local private data. Nevertheless, recent studies show that conventional FL algorithms still exhibit deficiencies in privacy protection, and the server lacks a reliable and stable aggregation rule for updating the global model.