Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training
This addresses data heterogeneity for federated learning applications, representing an incremental improvement over existing methods.
The paper tackles data heterogeneity in federated learning by proposing FedSB, which uses label smoothing and balanced decentralized training to enhance generalization across domains, achieving state-of-the-art results on three out of four multi-domain datasets.
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.