Dynamic Clustering for Personalized Federated Learning on Heterogeneous Edge Devices

TL;DR

This paper introduces a dynamic clustering algorithm for personalized federated learning that adapts client groupings based on data similarity, improving training efficiency and model accuracy on heterogeneous edge devices.

Contribution

It proposes a novel model discrepancy metric to estimate data heterogeneity without raw data exposure and a dynamic clustering method that enhances federated learning personalization.

Findings

Reduces total training time significantly.

Improves model accuracy over baseline methods.

Decreases communication costs through layer-wise aggregation.

Abstract

Federated Learning (FL) enables edge devices to collaboratively learn a global model, but it may not perform well when clients have high data heterogeneity. In this paper, we propose a dynamic clustering algorithm for personalized federated learning system (DC-PFL) to address the problem of data heterogeneity. DC-PFL starts with all clients training a global model and gradually groups the clients into smaller clusters for model personalization based on their data similarities. To address the challenge of estimating data heterogeneity without exposing raw data, we introduce a discrepancy metric called model discrepancy, which approximates data heterogeneity solely based on the model weights received by the server. We demonstrate that model discrepancy is strongly and positively correlated with data heterogeneity and can serve as a reliable indicator of data heterogeneity. To determine when and how to change grouping structures, we propose an algorithm based on the rapid decrease period of the training loss curve. Moreover, we propose a layer-wise aggregation mechanism that aggregates the low-discrepancy layers at a lower frequency to reduce the amount of transmitted data and communication costs. We conduct extensive experiments on various datasets to evaluate our proposed algorithm, and our results show that DC-PFL significantly reduces total training time and improves model accuracy compared to baselines.