Research into Robust Federated Learning Methods Driven by Heterogeneity Awareness

Federated learning (FL) has emerged as a prominent distributed machine learning paradigm that facilitates collaborative model training across multiple clients while ensuring data privacy. Despite its growing adoption in practical applications, performance degradation caused by data heterogeneity—com...

Full description

Saved in:
Bibliographic Details
Main Authors: Junhui Song, Zhangqi Zheng, Afei Li, Zhixin Xia, Yongshan Liu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/14/7843
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246567604682752
author Junhui Song
Zhangqi Zheng
Afei Li
Zhixin Xia
Yongshan Liu
author_facet Junhui Song
Zhangqi Zheng
Afei Li
Zhixin Xia
Yongshan Liu
author_sort Junhui Song
collection DOAJ
description Federated learning (FL) has emerged as a prominent distributed machine learning paradigm that facilitates collaborative model training across multiple clients while ensuring data privacy. Despite its growing adoption in practical applications, performance degradation caused by data heterogeneity—commonly referred to as the non-independent and identically distributed (non-IID) nature of client data—remains a fundamental challenge. To mitigate this issue, a heterogeneity-aware and robust FL framework is proposed to enhance model generalization and stability under non-IID conditions. The proposed approach introduces two key innovations. First, a heterogeneity quantification mechanism is designed based on statistical feature distributions, enabling the effective measurement of inter-client data discrepancies. This metric is further employed to guide the model aggregation process through a heterogeneity-aware weighted strategy. Second, a multi-loss optimization scheme is formulated, integrating classification loss, heterogeneity loss, feature center alignment, and L2 regularization for improved robustness against distributional shifts during local training. Comprehensive experiments are conducted on four benchmark datasets, including CIFAR-10, SVHN, MNIST, and NotMNIST under Dirichlet-based heterogeneity settings (alpha = 0.1 and alpha = 0.5). The results demonstrate that the proposed method consistently outperforms baseline approaches such as FedAvg, FedProx, FedSAM, and FedMOON. Notably, an accuracy improvement of approximately 4.19% over FedSAM is observed on CIFAR-10 (alpha = 0.5), and a 1.82% gain over FedMOON on SVHN (alpha = 0.1), along with stable enhancements on MNIST and NotMNIST. Furthermore, ablation studies confirm the contribution and necessity of each component in addressing data heterogeneity.
format Article
id doaj-art-8d508948f4e8445b96fc275db72cc7c9
institution Kabale University
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-8d508948f4e8445b96fc275db72cc7c92025-08-20T03:58:27ZengMDPI AGApplied Sciences2076-34172025-07-011514784310.3390/app15147843Research into Robust Federated Learning Methods Driven by Heterogeneity AwarenessJunhui Song0Zhangqi Zheng1Afei Li2Zhixin Xia3Yongshan Liu4School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Mathematics and Information Technology, Hebei Normal University of Science & Technology, Qinhuangdao 066004, ChinaSchool of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, ChinaSchool of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, ChinaFederated learning (FL) has emerged as a prominent distributed machine learning paradigm that facilitates collaborative model training across multiple clients while ensuring data privacy. Despite its growing adoption in practical applications, performance degradation caused by data heterogeneity—commonly referred to as the non-independent and identically distributed (non-IID) nature of client data—remains a fundamental challenge. To mitigate this issue, a heterogeneity-aware and robust FL framework is proposed to enhance model generalization and stability under non-IID conditions. The proposed approach introduces two key innovations. First, a heterogeneity quantification mechanism is designed based on statistical feature distributions, enabling the effective measurement of inter-client data discrepancies. This metric is further employed to guide the model aggregation process through a heterogeneity-aware weighted strategy. Second, a multi-loss optimization scheme is formulated, integrating classification loss, heterogeneity loss, feature center alignment, and L2 regularization for improved robustness against distributional shifts during local training. Comprehensive experiments are conducted on four benchmark datasets, including CIFAR-10, SVHN, MNIST, and NotMNIST under Dirichlet-based heterogeneity settings (alpha = 0.1 and alpha = 0.5). The results demonstrate that the proposed method consistently outperforms baseline approaches such as FedAvg, FedProx, FedSAM, and FedMOON. Notably, an accuracy improvement of approximately 4.19% over FedSAM is observed on CIFAR-10 (alpha = 0.5), and a 1.82% gain over FedMOON on SVHN (alpha = 0.1), along with stable enhancements on MNIST and NotMNIST. Furthermore, ablation studies confirm the contribution and necessity of each component in addressing data heterogeneity.https://www.mdpi.com/2076-3417/15/14/7843federated learningdata heterogeneityheterogeneity-awareweighted aggregationmulti-loss function
spellingShingle Junhui Song
Zhangqi Zheng
Afei Li
Zhixin Xia
Yongshan Liu
Research into Robust Federated Learning Methods Driven by Heterogeneity Awareness
Applied Sciences
federated learning
data heterogeneity
heterogeneity-aware
weighted aggregation
multi-loss function
title Research into Robust Federated Learning Methods Driven by Heterogeneity Awareness
title_full Research into Robust Federated Learning Methods Driven by Heterogeneity Awareness
title_fullStr Research into Robust Federated Learning Methods Driven by Heterogeneity Awareness
title_full_unstemmed Research into Robust Federated Learning Methods Driven by Heterogeneity Awareness
title_short Research into Robust Federated Learning Methods Driven by Heterogeneity Awareness
title_sort research into robust federated learning methods driven by heterogeneity awareness
topic federated learning
data heterogeneity
heterogeneity-aware
weighted aggregation
multi-loss function
url https://www.mdpi.com/2076-3417/15/14/7843
work_keys_str_mv AT junhuisong researchintorobustfederatedlearningmethodsdrivenbyheterogeneityawareness
AT zhangqizheng researchintorobustfederatedlearningmethodsdrivenbyheterogeneityawareness
AT afeili researchintorobustfederatedlearningmethodsdrivenbyheterogeneityawareness
AT zhixinxia researchintorobustfederatedlearningmethodsdrivenbyheterogeneityawareness
AT yongshanliu researchintorobustfederatedlearningmethodsdrivenbyheterogeneityawareness