Mostrar el registro sencillo del ítem

dc.contributor.authorMorell, José Ángel
dc.contributor.authorAbdelmoiz Dahi, Zakaria
dc.contributor.authorChicano-García, José-Francisco 
dc.contributor.authorLuque-Polo, Gabriel Jesús 
dc.contributor.authorAlba-Torres, Enrique 
dc.date.accessioned2024-03-14T11:55:38Z
dc.date.available2024-03-14T11:55:38Z
dc.date.issued2024-02-24
dc.identifier.citationJosé Ángel Morell, Zakaria Abdelmoiz Dahi, Francisco Chicano, Gabriel Luque, Enrique Alba, A multi-objective approach for communication reduction in federated learning under devices heterogeneity constraints, Future Generation Computer Systems, Volume 155, 2024, Pages 367-383, ISSN 0167-739X, https://doi.org/10.1016/j.future.2024.02.022es_ES
dc.identifier.urihttps://hdl.handle.net/10630/30831
dc.description.abstractFederated learning is a paradigm that proposes protecting data privacy by sharing local models instead of raw data during each iteration of model training. However, these models can be large, with many parameters, provoking a substantial communication cost and having a notable environmental impact. Reducing communication overhead is paramount but conflictual to maintaining the model’s accuracy. Most research has dealt with the different factors influencing communication reduction separately without addressing their correlations. Moreover, most of them do not consider the heterogeneity of clients’ hardware. Finding the optimal configuration to fulfil all these training aspects can become intractable for classical techniques. This work explores the add-in that multi-objective evolutionary algorithms can provide for solving the communication overhead problem while achieving high accuracy. We do this by 1) realistically modelling and formulating this task as a multi-objective problem by considering the devices’ heterogeneity, 2) including all the communication-triggering aspects, and 3) applying a multi-objective evolutionary algorithm with an intensification operator to solve the problem. A simulated client–server architecture of four devices with four different processing speeds is studied. Both fully connected and convolutional neural network models are investigated with 33,400 and 887,530 weights, respectively. The experiments are performed using the MNIST and Fashion-MNIST datasets. A comparison is made between three approaches using an extensive set of metrics. Results prove that our approach obtains solutions with better accuracy than the full-communication setting and other methods while getting reductions in communications by around 1,000 times in most cases and up to 10,000 times in some cases compared to the maximum communication setting.es_ES
dc.description.sponsorshipFunding for open access charge: Universidad de Málaga / CBUA. This research is funded by PID 2020-116727RB-I00 (HUmove) funded by MCIN/AEI/ 10.13039/501100011033, Spain; and TAILOR ICT-48 Network (No 952215) funded by EU Horizon 2020 research and innovation programme, Spain. The authors thank the Supercomputing and Bioinnovation Center (SCBI) for their provision of computational resources and technical support.es_ES
dc.language.isoenges_ES
dc.publisherElsevieres_ES
dc.rightsinfo:eu-repo/semantics/openAccesses_ES
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectInformáticaes_ES
dc.subjectAlgoritmos genéticoses_ES
dc.subjectRedes neuronales (Informática)es_ES
dc.subject.otherCommunication costes_ES
dc.subject.otherFederated learninges_ES
dc.subject.otherGenetic algorithmes_ES
dc.subject.otherModel compressiones_ES
dc.subject.otherMulti-objective optimisationes_ES
dc.subject.otherNeural networkes_ES
dc.titleA multi-objective approach for communication reduction in federated learning under devices heterogeneity constraintses_ES
dc.typeinfo:eu-repo/semantics/articlees_ES
dc.centroE.T.S.I. Informáticaes_ES
dc.identifier.doi10.1016/j.future.2024.02.022
dc.rights.ccAtribución 4.0 Internacional*
dc.type.hasVersioninfo:eu-repo/semantics/publishedVersiones_ES


Ficheros en el ítem

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem

Atribución 4.0 Internacional
Excepto si se señala otra cosa, la licencia del ítem se describe como Atribución 4.0 Internacional