FedNolowe: A Normalized Loss-Based Weighted Aggregation Strategy for Robust Federated Learning in Heterogeneous Environments
Duy-Dong Le, Nguyen Huynh Tuong, Anh-Khoa Tran, Minh-Son Dao, Pham The Bao
FedNolowe improves federated learning stability by weighting client contributions based on normalized losses, achieving state-of-the-art performance with reduced computational complexity.
PLoS ONE · Aug 14, 2025Peer-reviewedBioinformatics