2025
Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training
ICASSP 2025accepted
In this paper, we propose a novel approach, Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training (FedSB), to address the challenges of data heterogeneity within a federated learning framework. FedSB utilizes label smoothing at the client level to prevent overfitti…