解决联邦学习中数据异构问题，提升跨域泛化能力。
Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training
- 客户端使用标签平滑防止过拟合特定领域特征
- 采用去中心化预算机制平衡各客户端训练，提升全局模型性能
- 在四个数据集上三项领先，适合跨域场景的联邦学习应用
本文提出一种新方法 FedSB（Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training），以应对联邦学习框架内数据异构性的挑战。FedSB 在客户端层面引入标签平滑，避免对特定领域特征的过拟合，从而增强本地模型聚合后在多样化域上的泛化能力。同时，该方法设计了一种去中心化预算机制，均衡各客户端间的训练负荷，显著提升全局模型性能。在 PACS、VLCS、OfficeHome 与 TerraInc 四个常用多域数据集上的大量实验表明，FedSB 在三个数据集上达到当前最优表现，验证了其在缓解数据异构性方面的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。