Data Heterogeneity-Aware Client Selection for Federated Learning in Wireless Networks

TL;DR

This paper analyzes how data heterogeneity affects federated learning in wireless networks and proposes a client selection method that improves accuracy, reduces latency, and saves energy by considering data diversity.

Contribution

It introduces a theoretical framework for data heterogeneity impact and develops a joint client selection and resource allocation approach to optimize FL performance.

Findings

Higher test accuracy with proposed scheme

Reduced learning latency compared to baselines

Lower energy consumption in simulations

Abstract

Federated Learning (FL) enables mobile edge devices, functioning as clients, to collaboratively train a decentralized model while ensuring local data privacy. However, the efficiency of FL in wireless networks is limited not only by constraints on communication and computational resources but also by significant data heterogeneity among clients, particularly in large-scale networks. This paper first presents a theoretical analysis of the impact of client data heterogeneity on global model generalization error, which can result in repeated training cycles, increased energy consumption, and prolonged latency. Based on the theoretical insights, an optimization problem is formulated to jointly minimize learning latency and energy consumption while constraining generalization error. A joint client selection and resource allocation (CSRA) approach is then proposed, employing a series of convex optimization and relaxation techniques. Extensive simulation results demonstrate that the proposed CSRA scheme yields higher test accuracy, reduced learning latency, and lower energy consumption compared to baseline methods that do not account for data heterogeneity.