FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering
This addresses a critical problem for federated learning systems dealing with heterogeneous client data, though it appears incremental as it builds on existing cluster-based approaches.
The paper tackles the challenge of multiple simultaneous distribution shifts in federated learning, such as feature, label, and concept shifts, by proposing FedRC, a robust clustering algorithm that significantly outperforms state-of-the-art cluster-based FL methods.
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}.