Federated learning is a decentralized and privacy-preserving technique that enables multiple clients to collaborate with a server to learn a global model without exposing their private data. However, the presence of statistical heterogeneity among clients poses a challenge, as the global model may struggle to perform well on each client's specific task. To address this issue, we introduce a new perspective on personalized federated learning through Amortized Bayesian Meta-Learning. Specifically, we propose a novel algorithm called \emph{FedABML}, which employs hierarchical variational inference across clients. The global prior aims to capture representations of common intrinsic structures from heterogeneous clients, which can then be transferred to their respective tasks and aid in the generation of accurate client-specific approximate posteriors through a few local updates. Our theoretical analysis provides an upper bound on the average generalization error and guarantees the generalization performance on unseen data. Finally, several empirical results are implemented to demonstrate that \emph{FedABML} outperforms several competitive baselines.

翻译：联邦学习是一种去中心化且保护隐私的技术，允许多个客户端与服务器协作学习全局模型，同时避免暴露其私有数据。然而，客户端之间的统计异质性带来了挑战，因为全局模型可能难以在每个客户端的特定任务上表现良好。为应对这一问题，我们通过摊销贝叶斯元学习引入了个性化联邦学习的新视角。具体而言，我们提出了一种名为\emph{FedABML}的新算法，该算法在客户端间采用分层变分推理。全局先验旨在从异质客户端中捕捉常见内在结构的表征，这些表征可被迁移至各自任务，并通过少量本地更新辅助生成准确的客户端特定近似后验。我们的理论分析提供了平均泛化误差的上界，并保证了未见数据上的泛化性能。最后，通过多项实验结果验证了\emph{FedABML}优于多个竞争基线方法。