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 overfitting to domain-specific features, thereby enhancing generalization capabilities across diverse domains when aggregating local models into a global model. Additionally, FedSB incorporates a decentralized budgeting mechanism which balances training among clients, which is shown to improve the performance of the aggregated global model. Extensive experiments on four commonly used multi-domain datasets, PACS, VLCS, OfficeHome, and TerraInc, demonstrate that FedSB outperforms competing methods, achieving state-of-the-art results on three out of four datasets, indicating the effectiveness of FedSB in addressing data heterogeneity.
@article{arxiv.2412.11408,
title = {Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training},
author = {Milad Soltany and Farhad Pourpanah and Mahdiyar Molahasani and Michael Greenspan and Ali Etemad},
journal= {arXiv preprint arXiv:2412.11408},
year = {2025}
}