Publication:
Fedstellar: a platform for decentralized federated learning

Simple item page
dc.contributor.authorMartínez Beltrán, Enrique Tomás
dc.contributor.authorPerales Gómez, Ángel Luis
dc.contributor.authorFeng, Chao
dc.contributor.authorSánchez Sánchez, Pedro Miguel
dc.contributor.authorLópez Bernal, Sergio
dc.contributor.authorGérôme, Bovet
dc.contributor.authorGil Pérez, Manuel
dc.contributor.authorMartínez Pérez, Gregorio
dc.contributor.authorHuertas Celdrán, Alberto
dc.contributor.departmentIngeniería y Tecnología de Computadores
dc.date.accessioned2024-06-28T08:09:12Z
dc.date.available2024-06-28T08:09:12Z
dc.date.issued2024-05-14
dc.description© 2023 The Author(s). This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/ This document is the Published version of a Published Work that appeared in final form in Expert Systems with Applications. To access the final edited and published work see https://doi.org/10.1016/j.eswa.2023.122861
dc.description.abstractIn 2016, Google proposed Federated Learning (FL) as a novel paradigm to train Machine Learning (ML) models across the participants of a federation while preserving data privacy. Since its birth, Centralized FL (CFL) has been the most used approach, where a central entity aggregates participants’ models to create a global one. However, CFL presents limitations such as communication bottlenecks, single point of failure, and reliance on a central server. Decentralized Federated Learning (DFL) addresses these issues by enabling decentralized model aggregation and minimizing dependency on a central entity. Despite these advances, current platforms training DFL models struggle with key issues such as managing heterogeneous federation network topologies, adapting the FL process to virtualized or physical deployments, and using a limited number of metrics to evaluate different federation scenarios for efficient implementation. To overcome these challenges, this paper presents Fedstellar, a novel platform designed to train FL models in a decentralized, semi-decentralized, and centralized fashion across diverse federations of physical or virtualized devices. Fedstellar allows users to create federations by customizing parameters like the number and type of devices training FL models, the network topology connecting them, the machine and deep learning algorithms, or the datasets of each participant, among others. Additionally, it offers real-time monitoring of model and network performance. The Fedstellar implementation encompasses a web application with an interactive graphical interface, a controller for deploying federations of nodes using physical or virtual devices, and a core deployed on each device, which provides the logic needed to train, aggregate, and communicate in the network. The effectiveness of the platform has been demonstrated in two scenarios: a physical deployment involving single-board devices such as Raspberry Pis for detecting cyberattacks and a virtualized deployment comparing various FL approaches in a controlled environment using MNIST and CIFAR-10 datasets. In both scenarios, Fedstellar demonstrated consistent performance and adaptability, achieving of 91%, 98%, and 91.2% using DFL for detecting cyberattacks and classifying MNIST and CIFAR-10, respectively, reducing training time by 32% compared to centralized approaches.es
dc.formatapplication/pdfes
dc.format.extent15
dc.identifier.citationExpert Systems with Applications, 2024, Vol. 242: 122861
dc.identifier.doihttps://doi.org/10.1016/j.eswa.2023.122861
dc.identifier.issnPrint: 0957-4174
dc.identifier.issnElectronic: 1873-6793
dc.identifier.urihttp://hdl.handle.net/10201/142732
dc.languageenges
dc.publisherElsevier
dc.relationThis work has been partially supported by (a) 21629/FPI/21, Fundación Séneca, Región de Murcia (Spain), (b) the strategic project DEFENDER from the Spanish National Institute of Cybersecurity(INCIBE) and by the Recovery, Transformation and Resilience Plan, Next Generation EU, (c) the Swiss Federal Office for Defense Procurement (armasuisse) with the DEFENDIS and CyberForce projects (CYD-C-2020003), (d) the University of Zürich UZH, (e) MCIN/AEI/10.13039/501100011033, NextGenerationEU/PRTR, UE, under grant TED2021-129300B-I00, and (f) MCIN/AEI/10.13039/501100011033/FEDER , UE, under grant PID2021-122466OB-I00.es
dc.relation.publisherversionhttps://www.sciencedirect.com/science/article/pii/S0957417423033638?via%3Dihub#d1e2723
dc.rightsinfo:eu-repo/semantics/openAccesses
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internacional*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/*
dc.subjectDecentralized federated learning
dc.subjectDeep learning
dc.subjectCollaborative training
dc.subjectCommunication mechanisms
dc.titleFedstellar: a platform for decentralized federated learninges
dc.typeinfo:eu-repo/semantics/articlees
dspace.entity.typePublicationes
relation.isAuthorOfPublication155e7fdb-63ef-47a4-8068-bc025cfbabb9
relation.isAuthorOfPublication.latestForDiscovery155e7fdb-63ef-47a4-8068-bc025cfbabb9
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1-s2.0-S0957417423033638-main.pdf
Size:
2.96 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.26 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Artículos