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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yanbing, Zhu, Huiling, Cheng, Wenchi, Wang, Jingqing, Chen, Changrun, Wang, Jiangzhou
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914227284869120
author Yang, Yanbing
Zhu, Huiling
Cheng, Wenchi
Wang, Jingqing
Chen, Changrun
Wang, Jiangzhou
author_facet Yang, Yanbing
Zhu, Huiling
Cheng, Wenchi
Wang, Jingqing
Chen, Changrun
Wang, Jiangzhou
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24286
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Data Heterogeneity-Aware Client Selection for Federated Learning in Wireless Networks
Yang, Yanbing
Zhu, Huiling
Cheng, Wenchi
Wang, Jingqing
Chen, Changrun
Wang, Jiangzhou
Distributed, Parallel, and Cluster Computing
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.
title Data Heterogeneity-Aware Client Selection for Federated Learning in Wireless Networks
topic Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2512.24286