Submit

Login Login

Register Register

Home / Journals / CMC / Online First / doi:10.32604/cmc.2026.083715
Journal Menu
Special Issues
Table of Content

All issues

Online First

2026

2025

2024

2023

2022

2021

2020

2019

2018

2017

2016

2015

2014

2013

2012

2011

2010

2009

2008

2007

2006

2005

2004

Open Access

ARTICLE

Federated Learning with Consistency Optimization Algorithms under Non-IID Data

Rui Wu1, Yehong Li2, Hongjie Guo3,*, Gangqiang Hu3, Changjun Zhou3,*, Qile Zou4
1 School of Software Engineering, Jiangxi University of Science and Technology, Nanchang, China
2 Jiangxi Provincial Key Laboratory of Multidimensional Intelligent Perception and Control, Jiangxi University of Science and Technology, Ganzhou, China
3 School of Computer Science and Technology, Zhejiang Normal University, Jinhua, China
4 Faculty of Science and Engineering, University of Nottingham Ningbo China, Ningbo, China
* Corresponding Author: Hongjie Guo. Email: email; Changjun Zhou. Email: email

Computers, Materials & Continua https://doi.org/10.32604/cmc.2026.083715

Received 09 April 2026; Accepted 03 July 2026; Published online 29 July 2026

Abstract

Federated learning (FL) enables collaborative training of deep neural architectures while preserving data privacy, yet its performance often deteriorates in non-IID scenarios, which stems from client-side distribution drift and divergent local updates induced by pervasive data heterogeneity. This challenge is particularly critical for maintaining the structural consistency and generalization of neural models across diverse, distributed sources with significant distribution shifts. In this paper, we investigate how to effectively mitigate label distribution shift and feature distribution skew to enhance the global representation stability of neural architectures. We propose Federated Learning with Consistency Optimization Algorithms (FedCO), a novel optimization framework that incorporates a label-skew-aware correction loss and neural feature distribution regularization during local training. Specifically, our method aligns the internal statistics of architectural components between local and global models to suppress feature-space drift. Combined with an adaptive global aggregation mechanism guided by label entropy, this approach ensures that model updates from heterogeneous clients are consistently integrated into the global architectural parameters. Experimental results on multiple benchmarks demonstrate that FedCO significantly improves accuracy and convergence under diverse non-IID settings. For instance, on CIFAR-10 with extreme heterogeneity (α=0.05), FedCO achieves 73.64% accuracy, outperforming FedAvg by 7.32%; it also attains the highest accuracies on CIFAR-100 (62.63%) and TinyImageNet (37.82%) under the same setting. Our findings provide a robust strategy for integrating distribution-aware local training with adaptive structural aggregation, offering new insights into enhancing the reliability of distributed neural systems in real-world deployments. The code related to this algorithm is available at https://github.com/Donglin0730/FedCO.

Keywords

Data heterogeneity; federated learning; federated optimization

  • 140

    View

  • 24

    Download

  • 0

    Like

Related articles
Copyright© 2026 Tech Science Press
© 1997-2026 TSP (Henderson, USA) unless otherwise stated

Share Link