Evaluating Local Update Strategies in FedAvg: Effects of Local Epochs and Client Participation on CIFAR-10

Xi Zeng

doi:10.54254/2753-8818/2026.CH29902

Theoretical and Natural ScienceOpen access

Evaluating Local Update Strategies in FedAvg: Effects of Local Epochs and Client Participation on CIFAR-10

Research Article

Open Access

Evaluating Local Update Strategies in FedAvg: Effects of Local Epochs and Client Participation on CIFAR-10

Xi Zeng ^1*

¹ University of California

^*Corresponding author: xizeng@ucdavis.edu

Published on 26 November 2025

TNS Vol.151

ISSN (Print): 2753-8826

ISSN (Online): 2753-8818

ISBN (Print): 978-1-80590-559-2

ISBN (Online): 978-1-80590-560-8

Download Cover

Abstract

This work studies federated learning on CIFAR-10 using a ResNet-18 classifier and three local update modes: plain Stochastic Gradient Descent (SGD), simulated Synchronous updates (Sync), and simulated Local updates (Local). An IID split provides a baseline to verify training and logging. The main experiments use a non-IID split and vary two factors while keeping all other hyperparameters fixed: the number of local epochs (E, tested at 2, 4, and 8) and the client participation rate (p, tested at 0.1, 0.2, 0.5, and 1.0). After each round, test accuracy, test loss, and per-round communication time (download, upload, aggregation) are recorded. Results show a consistent accuracy ranking across settings, with Local > Sync > SGD, most evident at high participation. Increasing local epochs from 2 to 4 and 8 preserves or slightly improves final accuracy and lowers per-round communication; the most stable communication profile occurs at E=8, with E=4 also markedly lower than E=2. Raising (dparticipation from 0.1 to 1.0 improves final accuracy and reduces round-to-round variance; at full participation, communication ordering is clearest, where Local lowest and Sync highest. A practical operating point emerges for this task and hardware: moderate-to-high participation with eight local epochs balances accuracy and communication.

Keywords:

Federated learning, Federated averaging (FedAvg), Non-IID data, Communication efficiency

View PDF

References

[1]. P. Kairouz et al., “Advances and Open Problems in Federated Learning, ” arXiv preprint arXiv: 1912.04977, 2021.

[2]. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data, ” arXiv preprint arXiv: 1602.05629, 2017.

[3]. A. Khaled, K. Mishchenko, and P. Richtárik, “First Analysis of Local GD on Heterogeneous Data, ” arXiv preprint arXiv: 1909.04715, 2019.

[4]. S. P. Karimireddy, S. Kale, M. Mohri, S. Reddi, S. Stich, and S. A. T. Suresh, “SCAFFOLD: Stochastic Controlled Averaging for Federated Learning, ” arXiv preprint arXiv: 1910.06378, 2020.

[5]. T. Li, A. K. Sahu, V. Smith, and V. Talwalkar, “Federated Optimization in Heterogeneous Networks, ” arXiv preprint arXiv: 1812.06127, 2020.

[6]. X. Lian, C. Zhang, H. Zhang, C.-J. Hsieh, W. Zhang, and J. Liu, “Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Parallel SGD, ” arXiv preprint arXiv: 1705.09056, 2017.

[7]. S. U. Stich, “Local SGD Converges Fast and Communicates Little, ” arXiv preprint arXiv: 1805.09767, 2019.

[8]. A. Krizhevsky and G. Hinton, Learning Multiple Layers of Features from Tiny Images, 2009.

[9]. L. Li, Y. Fan, M. Tse, and K. Y. Lin, “A review of applications in federated learning, ” Computers & Industrial Engineering, vol. 149, p. 106854, 2020.

[10]. J. Wen, Z. Zhang, Y. Lan, Z. Cui, J. Cai, and W. Zhang, “A survey on federated learning: challenges and applications, ” International Journal of Machine Learning and Cybernetics, vol. 14, no. 2, pp. 513–535, 2023.