PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.

Mingjia Shi, Yuhao Zhou, Kai Wang, Huaizheng Zhang, Shudong Huang, Qing Ye, Jiancheng Lv

Keywords: Federated Learning, Personalized Federated Learning, Expectation Maximization, Relaxed Mirror Descent

TL;DR: The paper proposes new PFL methods called pFedBreD that injects personalized prior knowledge into clients' global models to address the incomplete information problem with theoretical support, achieves state-of-the-art performance on 8 benchmarks.

Abstract: Classical federated learning (FL) enables training machine learning models without sharing data for privacy preservation, but heterogeneous data characteristic degrades the performance of the localized model. Personalized FL (PFL) addresses this by synthesizing personalized models from a global model via training on local data. Such a global model may overlook the specific information that the clients have been sampled. In this paper, we propose a novel scheme to inject personalized prior knowledge into the global model in each client, which attempts to mitigate the introduced incomplete information problem in PFL. At the heart of our proposed approach is a framework, the $\textit{PFL with Bregman Divergence}$ (pFedBreD), decoupling the personalized prior from the local objective function regularized by Bregman divergence for greater adaptability in personalized scenarios. We also relax the mirror descent (RMD) to extract the prior explicitly to provide optional strategies. Additionally, our pFedBreD is backed up by a convergence analysis. Sufficient experiments demonstrate that our method reaches the $\textit{state-of-the-art}$ performances on 5 datasets and outperforms other methods by up to 3.5% across 8 benchmarks. Extensive analyses verify the robustness and necessity of proposed designs. The code will be made public.

Submission Number: 2159