Enhancing global model accuracy in federated learning with deep neuro-fuzzy clustering cyclic algorithm

In recent years, with the increasing importance of privacy protection, many laws and regulations have standardized data usage, requiring companies to obtain user consent to access personal data. This has become more challenging for models that require large amounts of data for training. Therefore, t...

Full description

Saved in:
Bibliographic Details
Main Authors: Chin-Feng Lai, Ying-Hsun Lai, Ming-Chin Kao, Mu-Yen Chen
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Alexandria Engineering Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1110016824012584
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832583112751579136
author Chin-Feng Lai
Ying-Hsun Lai
Ming-Chin Kao
Mu-Yen Chen
author_facet Chin-Feng Lai
Ying-Hsun Lai
Ming-Chin Kao
Mu-Yen Chen
author_sort Chin-Feng Lai
collection DOAJ
description In recent years, with the increasing importance of privacy protection, many laws and regulations have standardized data usage, requiring companies to obtain user consent to access personal data. This has become more challenging for models that require large amounts of data for training. Therefore, the concept of federated learning was proposed in 2016, aiming to train models with different clients without sharing data to ensure data privacy. However, federated learning faces several challenges, including heterogeneous devices, data security, data heterogeneity, communication costs, and training time costs. This study focuses on addressing the issue of data heterogeneity, where the data distribution among participating clients differs significantly, leading to poor performance of the aggregated model after training. To tackle this problem, we propose a federated clustering cyclic algorithm, which involves two-step clustering of clients to make the data distribution of each cluster approach independent and identically distributed. We also introduce deep neural fuzzy methods to handle fuzzy, uncertain, or incomplete data. According to experimental results, the proposed deep neuro-fuzzy clustered cyclic algorithm outperforms methods such as FedAvg, FedProx, and CyclicFL on various non-IID datasets, with accuracy approaching that of centralized learning in certain experiments. This indicates that the deep neural fuzzy methods and clustering cyclic algorithm DNCC presented in this study can improve the accuracy of global models, especially in increasingly non-IID scenarios. Furthermore, we extend this method to big data processing to cope with more complex data environments.
format Article
id doaj-art-afc4301757c04d249becfb02f2cd0704
institution Kabale University
issn 1110-0168
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Alexandria Engineering Journal
spelling doaj-art-afc4301757c04d249becfb02f2cd07042025-01-29T05:00:09ZengElsevierAlexandria Engineering Journal1110-01682025-01-01112474486Enhancing global model accuracy in federated learning with deep neuro-fuzzy clustering cyclic algorithmChin-Feng Lai0Ying-Hsun Lai1Ming-Chin Kao2Mu-Yen Chen3National Cheng Kung University, No. 1, University Rd., Tainan, 70101, TaiwanNational Taitung University, No. 369, Sec. 2, University Rd., Taitung, 950309, TaiwanIndustrial Technology Research Institute, 195, Sec. 4, Chung Hsing Rd., Hsinchu, 300096, TaiwanNational Cheng Kung University, No. 1, University Rd., Tainan, 70101, Taiwan; Corresponding author.In recent years, with the increasing importance of privacy protection, many laws and regulations have standardized data usage, requiring companies to obtain user consent to access personal data. This has become more challenging for models that require large amounts of data for training. Therefore, the concept of federated learning was proposed in 2016, aiming to train models with different clients without sharing data to ensure data privacy. However, federated learning faces several challenges, including heterogeneous devices, data security, data heterogeneity, communication costs, and training time costs. This study focuses on addressing the issue of data heterogeneity, where the data distribution among participating clients differs significantly, leading to poor performance of the aggregated model after training. To tackle this problem, we propose a federated clustering cyclic algorithm, which involves two-step clustering of clients to make the data distribution of each cluster approach independent and identically distributed. We also introduce deep neural fuzzy methods to handle fuzzy, uncertain, or incomplete data. According to experimental results, the proposed deep neuro-fuzzy clustered cyclic algorithm outperforms methods such as FedAvg, FedProx, and CyclicFL on various non-IID datasets, with accuracy approaching that of centralized learning in certain experiments. This indicates that the deep neural fuzzy methods and clustering cyclic algorithm DNCC presented in this study can improve the accuracy of global models, especially in increasingly non-IID scenarios. Furthermore, we extend this method to big data processing to cope with more complex data environments.http://www.sciencedirect.com/science/article/pii/S1110016824012584Federated learningNon-IID dataDeep neuro-fuzzy clusteringCyclic trainingModel convergence
spellingShingle Chin-Feng Lai
Ying-Hsun Lai
Ming-Chin Kao
Mu-Yen Chen
Enhancing global model accuracy in federated learning with deep neuro-fuzzy clustering cyclic algorithm
Alexandria Engineering Journal
Federated learning
Non-IID data
Deep neuro-fuzzy clustering
Cyclic training
Model convergence
title Enhancing global model accuracy in federated learning with deep neuro-fuzzy clustering cyclic algorithm
title_full Enhancing global model accuracy in federated learning with deep neuro-fuzzy clustering cyclic algorithm
title_fullStr Enhancing global model accuracy in federated learning with deep neuro-fuzzy clustering cyclic algorithm
title_full_unstemmed Enhancing global model accuracy in federated learning with deep neuro-fuzzy clustering cyclic algorithm
title_short Enhancing global model accuracy in federated learning with deep neuro-fuzzy clustering cyclic algorithm
title_sort enhancing global model accuracy in federated learning with deep neuro fuzzy clustering cyclic algorithm
topic Federated learning
Non-IID data
Deep neuro-fuzzy clustering
Cyclic training
Model convergence
url http://www.sciencedirect.com/science/article/pii/S1110016824012584
work_keys_str_mv AT chinfenglai enhancingglobalmodelaccuracyinfederatedlearningwithdeepneurofuzzyclusteringcyclicalgorithm
AT yinghsunlai enhancingglobalmodelaccuracyinfederatedlearningwithdeepneurofuzzyclusteringcyclicalgorithm
AT mingchinkao enhancingglobalmodelaccuracyinfederatedlearningwithdeepneurofuzzyclusteringcyclicalgorithm
AT muyenchen enhancingglobalmodelaccuracyinfederatedlearningwithdeepneurofuzzyclusteringcyclicalgorithm