Federated learning has attracted increasing attention to building models without accessing the raw user data, especially in healthcare. In real applications, different federations can seldom work together due to possible reasons such as data heterogeneity and distrust/inexistence of the central server. In this paper, we propose a novel framework called MetaFed to facilitate trustworthy FL between different federations. MetaFed obtains a personalized model for each federation without a central server via the proposed Cyclic Knowledge Distillation. Specifically, MetaFed treats each federation as a meta distribution and aggregates knowledge of each federation in a cyclic manner. The training is split into two parts: common knowledge accumulation and personalization. Comprehensive experiments on three benchmarks demonstrate that MetaFed without a server achieves better accuracy compared to state-of-the-art methods (e.g., 10%+ accuracy improvement compared to the baseline for PAMAP2) with fewer communication costs.

翻译：联邦学习因无需访问原始用户数据即可构建模型而备受关注，尤其在医疗领域。实际应用中，由于数据异构性、中央服务器的不可信或缺失等原因，不同联邦间往往难以协同工作。本文提出一种名为MetaFed的新框架，旨在促进不同联邦间的可信联邦学习。MetaFed通过提出的循环知识蒸馏机制，无需中央服务器即可为每个联邦获得个性化模型。具体而言，MetaFed将每个联邦视为一个元分布，并以循环方式聚合各联邦的知识。训练过程分为两个部分：公共知识积累与个性化。在三个基准数据集上的综合实验表明，与最先进方法相比（例如，在PAMAP2数据集上相比基线方法准确率提升超过10%），MetaFed无需服务器即可实现更高精度，同时通信成本更低。