FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering

TL;DR

This paper introduces FedRC, a robust clustering framework for federated learning that effectively handles multiple simultaneous distribution shifts among clients, improving global model performance in heterogeneous environments.

Contribution

The paper proposes a novel clustering algorithm framework, FedRC, that addresses the challenge of diverse and simultaneous distribution shifts in federated learning.

Findings

FedRC significantly outperforms existing cluster-based FL methods.

The proposed bi-level optimization and objective function enhance robustness to distribution shifts.

Extensive experiments validate the effectiveness of FedRC in heterogeneous settings.

Abstract

Federated Learning (FL) is a machine learning paradigm that safeguards privacy by retaining client data on edge devices. However, optimizing FL in practice can be challenging due to the diverse and heterogeneous nature of the learning system. Though recent research has focused on improving the optimization of FL when distribution shifts occur among clients, ensuring global performance when multiple types of distribution shifts occur simultaneously among clients -- such as feature distribution shift, label distribution shift, and concept shift -- remain under-explored. In this paper, we identify the learning challenges posed by the simultaneous occurrence of diverse distribution shifts and propose a clustering principle to overcome these challenges. Through our research, we find that existing methods fail to address the clustering principle. Therefore, we propose a novel clustering algorithm framework, dubbed as FedRC, which adheres to our proposed clustering principle by incorporating a bi-level optimization problem and a novel objective function. Extensive experiments demonstrate that FedRC significantly outperforms other SOTA cluster-based FL methods. Our code is available at \url{https://github.com/LINs-lab/FedRC}.