FedStein：通过James-Stein估计器增强多域联邦学习
FedStein: Enhancing Multi-Domain Federated Learning Through James-Stein Estimator
AI总结：
FedStein针对多域联邦学习中特征分布差异问题，提出仅共享批量归一化统计量的James-Stein估计值而保留本地BN参数的方法，在多个数据集上准确率提升超14%，优于FedAvg和FedBN。
摘要：
联邦学习（FL）通过在分散的客户端之间进行协作式原位训练来促进数据隐私保护。尽管FL具有固有优势，但在处理非独立同分布（non-i.i.d.）数据时，FL在性能和收敛方面面临重大挑战。以往的研究主要解决客户端之间标签分布偏斜的问题，而本研究聚焦于较少被探索的多域联邦学习挑战，即客户端数据来自具有不同特征分布的不同域。我们提出了一种新方法FedStein：通过James-Stein估计器增强多域联邦学习。FedStein的独特之处在于仅在客户端之间共享批量归一化（BN）统计量的James-Stein（JS）估计值，同时保持本地BN参数不变。非BN层参数通过标准FL技术进行交换。在三个数据集和多个模型上进行的大量实验表明，FedStein超越了FedAvg和FedBN等现有方法，在某些域中准确率提升超过14%，从而增强了域泛化能力。代码可在https://github.com/sunnyinAI/FedStein获取。
英文摘要：
Federated Learning (FL) facilitates data privacy by enabling collaborative in-situ training across decentralized clients. Despite its inherent advantages, FL faces significant challenges of performance and convergence when dealing with data that is not independently and identically distributed (non-i.i.d.). While previous research has primarily addressed the issue of skewed label distribution across clients, this study focuses on the less explored challenge of multi-domain FL, where client data originates from distinct domains with varying feature distributions. We introduce a novel method designed to address these challenges FedStein: Enhancing Multi-Domain Federated Learning Through the James-Stein Estimator. FedStein uniquely shares only the James-Stein (JS) estimates of batch normalization (BN) statistics across clients, while maintaining local BN parameters. The non-BN layer parameters are exchanged via standard FL techniques. Extensive experiments conducted across three datasets and multiple models demonstrate that FedStein surpasses existing methods such as FedAvg and FedBN, with accuracy improvements exceeding 14% in certain domains leading to enhanced domain generalization. The code is available at https://github.com/sunnyinAI/FedStein
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
