Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning

Federated learning (FL) is a distributed model for deep learning that integrates client-server architecture, edge computing, and real-time intelligence. FL has the capability of revolutionizing machine learning (ML) but lacks in the practicality of implementation due to technological limitations, co...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Shaashwat Agrawal, Sagnik Sarkar, Mamoun Alazab, Praveen Kumar Reddy Maddikunta, Thippa Reddy Gadekallu, Quoc-Viet Pham
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
Acceso en línea:	https://doaj.org/article/495259675b2345d1893d31851301e63a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:495259675b2345d1893d31851301e63a
record_format	dspace
spelling	oai:doaj.org-article:495259675b2345d1893d31851301e63a2021-11-29T00:56:24ZGenetic CFL: Hyperparameter Optimization in Clustered Federated Learning1687-527310.1155/2021/7156420https://doaj.org/article/495259675b2345d1893d31851301e63a2021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/7156420https://doaj.org/toc/1687-5273Federated learning (FL) is a distributed model for deep learning that integrates client-server architecture, edge computing, and real-time intelligence. FL has the capability of revolutionizing machine learning (ML) but lacks in the practicality of implementation due to technological limitations, communication overhead, non-IID (independent and identically distributed) data, and privacy concerns. Training a ML model over heterogeneous non-IID data highly degrades the convergence rate and performance. The existing traditional and clustered FL algorithms exhibit two main limitations, including inefficient client training and static hyperparameter utilization. To overcome these limitations, we propose a novel hybrid algorithm, namely, genetic clustered FL (Genetic CFL), that clusters edge devices based on the training hyperparameters and genetically modifies the parameters clusterwise. Then, we introduce an algorithm that drastically increases the individual cluster accuracy by integrating the density-based clustering and genetic hyperparameter optimization. The results are bench-marked using MNIST handwritten digit dataset and the CIFAR-10 dataset. The proposed genetic CFL shows significant improvements and works well with realistic cases of non-IID and ambiguous data. An accuracy of 99.79% is observed in the MNIST dataset and 76.88% in CIFAR-10 dataset with only 10 training rounds.Shaashwat AgrawalSagnik SarkarMamoun AlazabPraveen Kumar Reddy MaddikuntaThippa Reddy GadekalluQuoc-Viet PhamHindawi LimitedarticleComputer applications to medicine. Medical informaticsR858-859.7Neurosciences. Biological psychiatry. NeuropsychiatryRC321-571ENComputational Intelligence and Neuroscience, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Neurosciences. Biological psychiatry. Neuropsychiatry RC321-571 Shaashwat Agrawal Sagnik Sarkar Mamoun Alazab Praveen Kumar Reddy Maddikunta Thippa Reddy Gadekallu Quoc-Viet Pham Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning
description	Federated learning (FL) is a distributed model for deep learning that integrates client-server architecture, edge computing, and real-time intelligence. FL has the capability of revolutionizing machine learning (ML) but lacks in the practicality of implementation due to technological limitations, communication overhead, non-IID (independent and identically distributed) data, and privacy concerns. Training a ML model over heterogeneous non-IID data highly degrades the convergence rate and performance. The existing traditional and clustered FL algorithms exhibit two main limitations, including inefficient client training and static hyperparameter utilization. To overcome these limitations, we propose a novel hybrid algorithm, namely, genetic clustered FL (Genetic CFL), that clusters edge devices based on the training hyperparameters and genetically modifies the parameters clusterwise. Then, we introduce an algorithm that drastically increases the individual cluster accuracy by integrating the density-based clustering and genetic hyperparameter optimization. The results are bench-marked using MNIST handwritten digit dataset and the CIFAR-10 dataset. The proposed genetic CFL shows significant improvements and works well with realistic cases of non-IID and ambiguous data. An accuracy of 99.79% is observed in the MNIST dataset and 76.88% in CIFAR-10 dataset with only 10 training rounds.
format	article
author	Shaashwat Agrawal Sagnik Sarkar Mamoun Alazab Praveen Kumar Reddy Maddikunta Thippa Reddy Gadekallu Quoc-Viet Pham
author_facet	Shaashwat Agrawal Sagnik Sarkar Mamoun Alazab Praveen Kumar Reddy Maddikunta Thippa Reddy Gadekallu Quoc-Viet Pham
author_sort	Shaashwat Agrawal
title	Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning
title_short	Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning
title_full	Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning
title_fullStr	Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning
title_full_unstemmed	Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning
title_sort	genetic cfl: hyperparameter optimization in clustered federated learning
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/495259675b2345d1893d31851301e63a
work_keys_str_mv	AT shaashwatagrawal geneticcflhyperparameteroptimizationinclusteredfederatedlearning AT sagniksarkar geneticcflhyperparameteroptimizationinclusteredfederatedlearning AT mamounalazab geneticcflhyperparameteroptimizationinclusteredfederatedlearning AT praveenkumarreddymaddikunta geneticcflhyperparameteroptimizationinclusteredfederatedlearning AT thippareddygadekallu geneticcflhyperparameteroptimizationinclusteredfederatedlearning AT quocvietpham geneticcflhyperparameteroptimizationinclusteredfederatedlearning
_version_	1718407703269736448

Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning

Ejemplares similares