Fed-Hetero: A Self-Evaluating Federated Learning Framework for Data Heterogeneity

Federated learning (FL) enables deep learning models to be trained locally on devices without the need for data sharing, ensuring data privacy. However, when clients have uneven or imbalanced data distributions, it leads to data heterogeneity. Data heterogeneity can appear in different ways, often d...

Full description

Saved in:
Bibliographic Details
Main Authors: Aiswariya Milan Kummaya, Amudha Joseph, Kumar Rajamani, George Ghinea
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied System Innovation
Subjects:
Online Access:https://www.mdpi.com/2571-5577/8/2/28
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849712376965758976
author Aiswariya Milan Kummaya
Amudha Joseph
Kumar Rajamani
George Ghinea
author_facet Aiswariya Milan Kummaya
Amudha Joseph
Kumar Rajamani
George Ghinea
author_sort Aiswariya Milan Kummaya
collection DOAJ
description Federated learning (FL) enables deep learning models to be trained locally on devices without the need for data sharing, ensuring data privacy. However, when clients have uneven or imbalanced data distributions, it leads to data heterogeneity. Data heterogeneity can appear in different ways, often due to variations in label, data distributions, feature variations, and structural inconsistencies in the images. This can significantly impact FL performance, as the global model often struggles to achieve optimal convergence. To enhance training efficiency and model performance, a common strategy in FL is to exclude clients with limited data. However, excluding such clients can raise fairness concerns, particularly for smaller populations. To understand the influence of data heterogeneity, a self-evaluating federated learning framework for heterogeneity, <b>Fed-Hetero,</b> was designed to assess the type of heterogeneity associated with the clients and provide recommendations to clients to enhance the global model’s accuracy. Fed-Hetero thus enables the clients with limited data to participate in FL processes by adopting appropriate strategies that enhance model accuracy. The results show that Fed-Hetero identifies the client with heterogeneity and provides personalized recommendations.
format Article
id doaj-art-40ee08b9af7c46f1b9e86ab367a42fce
institution DOAJ
issn 2571-5577
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied System Innovation
spelling doaj-art-40ee08b9af7c46f1b9e86ab367a42fce2025-08-20T03:14:17ZengMDPI AGApplied System Innovation2571-55772025-02-01822810.3390/asi8020028Fed-Hetero: A Self-Evaluating Federated Learning Framework for Data HeterogeneityAiswariya Milan Kummaya0Amudha Joseph1Kumar Rajamani2George Ghinea3Department of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeedam, Bengaluru 560035, IndiaDepartment of Computer Science and Engineering, Amrita School of Computing, Amrita Vishwa Vidyapeedam, Bengaluru 560035, IndiaDepartment of AI, Marwadi University, Rajkot 360003, IndiaDepartment of Computer Science, Brunel University, London UB8 3PH, UKFederated learning (FL) enables deep learning models to be trained locally on devices without the need for data sharing, ensuring data privacy. However, when clients have uneven or imbalanced data distributions, it leads to data heterogeneity. Data heterogeneity can appear in different ways, often due to variations in label, data distributions, feature variations, and structural inconsistencies in the images. This can significantly impact FL performance, as the global model often struggles to achieve optimal convergence. To enhance training efficiency and model performance, a common strategy in FL is to exclude clients with limited data. However, excluding such clients can raise fairness concerns, particularly for smaller populations. To understand the influence of data heterogeneity, a self-evaluating federated learning framework for heterogeneity, <b>Fed-Hetero,</b> was designed to assess the type of heterogeneity associated with the clients and provide recommendations to clients to enhance the global model’s accuracy. Fed-Hetero thus enables the clients with limited data to participate in FL processes by adopting appropriate strategies that enhance model accuracy. The results show that Fed-Hetero identifies the client with heterogeneity and provides personalized recommendations.https://www.mdpi.com/2571-5577/8/2/28federated learningdata heterogeneityquantity skewlabel distribution skewimage skewFed-Hetero
spellingShingle Aiswariya Milan Kummaya
Amudha Joseph
Kumar Rajamani
George Ghinea
Fed-Hetero: A Self-Evaluating Federated Learning Framework for Data Heterogeneity
Applied System Innovation
federated learning
data heterogeneity
quantity skew
label distribution skew
image skew
Fed-Hetero
title Fed-Hetero: A Self-Evaluating Federated Learning Framework for Data Heterogeneity
title_full Fed-Hetero: A Self-Evaluating Federated Learning Framework for Data Heterogeneity
title_fullStr Fed-Hetero: A Self-Evaluating Federated Learning Framework for Data Heterogeneity
title_full_unstemmed Fed-Hetero: A Self-Evaluating Federated Learning Framework for Data Heterogeneity
title_short Fed-Hetero: A Self-Evaluating Federated Learning Framework for Data Heterogeneity
title_sort fed hetero a self evaluating federated learning framework for data heterogeneity
topic federated learning
data heterogeneity
quantity skew
label distribution skew
image skew
Fed-Hetero
url https://www.mdpi.com/2571-5577/8/2/28
work_keys_str_mv AT aiswariyamilankummaya fedheteroaselfevaluatingfederatedlearningframeworkfordataheterogeneity
AT amudhajoseph fedheteroaselfevaluatingfederatedlearningframeworkfordataheterogeneity
AT kumarrajamani fedheteroaselfevaluatingfederatedlearningframeworkfordataheterogeneity
AT georgeghinea fedheteroaselfevaluatingfederatedlearningframeworkfordataheterogeneity