A Tutorial on Federated Learning from Theory to Practice: Foundations, Software Frameworks, Exemplary Use Cases, and Selected Trends

Simple item page
dc.contributor.authorVictoria Luzon, M.
dc.contributor.authorRodriguez-Barroso, Nuria
dc.contributor.authorArgente-Garrido, Alberto
dc.contributor.authorJimenez-Lopez, Daniel
dc.contributor.authorMoyano, Jose M.
dc.contributor.authorDel Ser, Javier
dc.contributor.authorDing, Weiping
dc.contributor.authorHerrera, Francisco
dc.contributor.institutionIA
dc.date.accessioned2024-09-10T10:40:04Z
dc.date.available2024-09-10T10:40:04Z
dc.date.issued2024-04-01
dc.descriptionPublisher Copyright: © 2014 Chinese Association of Automation.
dc.description.abstractWhen data privacy is imposed as a necessity, Federated learning (FL) emerges as a relevant artificial intelligence field for developing machine learning (ML) models in a distributed and decentralized environment. FL allows ML models to be trained on local devices without any need for centralized data transfer, thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third parties. This paradigm has gained momentum in the last few years, spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data sources. By virtue of FL, models can be learned from all such distributed data sources while preserving data privacy. The aim of this paper is to provide a practical tutorial on FL, including a short methodology and a systematic analysis of existing software frameworks. Furthermore, our tutorial provides exemplary cases of study from three complementary perspectives: i) Foundations of FL, describing the main components of FL, from key elements to FL categories; ii) Implementation guidelines and exemplary cases of study, by systematically examining the functionalities provided by existing software frameworks for FL deployment, devising a methodology to design a FL scenario, and providing exemplary cases of study with source code for different ML approaches; and iii) Trends, shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL landscape. The ultimate purpose of this work is to establish itself as a referential work for researchers, developers, and data scientists willing to explore the capabilities of FL in practical applications.en
dc.description.statusPeer reviewed
dc.format.extent27
dc.identifier.citationVictoria Luzon , M , Rodriguez-Barroso , N , Argente-Garrido , A , Jimenez-Lopez , D , Moyano , J M , Del Ser , J , Ding , W & Herrera , F 2024 , ' A Tutorial on Federated Learning from Theory to Practice : Foundations, Software Frameworks, Exemplary Use Cases, and Selected Trends ' , IEEE/CAA Journal of Automatica Sinica , vol. 11 , no. 4 , pp. 824-850 . https://doi.org/10.1109/JAS.2024.124215
dc.identifier.doi10.1109/JAS.2024.124215
dc.identifier.issn2329-9266
dc.identifier.urihttps://hdl.handle.net/11556/4974
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85188530067&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofIEEE/CAA Journal of Automatica Sinica
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsData privacy
dc.subject.keywordsdistributed machine learning
dc.subject.keywordsfederated learning
dc.subject.keywordssoftware frameworks
dc.subject.keywordsControl and Systems Engineering
dc.subject.keywordsInformation Systems
dc.subject.keywordsControl and Optimization
dc.subject.keywordsArtificial Intelligence
dc.titleA Tutorial on Federated Learning from Theory to Practice: Foundations, Software Frameworks, Exemplary Use Cases, and Selected Trendsen
dc.typejournal article
Files