Federated learning: Overview, strategies, applications, tools and future directions

Basit Öğe Kaydı
dc.contributor.authorYurdem, Betul
dc.contributor.authorKuzlu, Murat
dc.contributor.authorGullu, Mehmet Kemal
dc.contributor.authorCatak, Ferhat Ozgur
dc.contributor.authorTabassum, Maliha
dc.date.accessioned2025-03-20T09:44:55Z
dc.date.available2025-03-20T09:44:55Z
dc.date.issued2024
dc.departmentİzmir Bakırçay Üniversitesi
dc.description.abstractFederated learning (FL) is a distributed machine learning process, which allows multiple nodes to work together to train a shared model without exchanging raw data. It offers several key advantages, such as data privacy, security, efficiency, and scalability, by keeping data local and only exchanging model updates through the communication network. This review paper provides a comprehensive overview of federated learning, including its principles, strategies, applications, and tools along with opportunities, challenges, and future research directions. The findings of this paper emphasize that federated learning strategies can significantly help overcome privacy and confidentiality concerns, particularly for high-risk applications. © 2024 The Author(s)
dc.identifier.doi10.1016/j.heliyon.2024.e38137
dc.identifier.issn2405-8440
dc.identifier.issue19
dc.identifier.scopus2-s2.0-85204992886
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.1016/j.heliyon.2024.e38137
dc.identifier.urihttps://hdl.handle.net/20.500.14034/2070
dc.identifier.volume10
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherElsevier Ltd
dc.relation.ispartofHeliyon
dc.relation.publicationcategoryDiğer
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_Scopus_20250319
dc.subjectData privacy
dc.subjectDistributed machine learning
dc.subjectFederated learning
dc.titleFederated learning: Overview, strategies, applications, tools and future directions
dc.typeReview

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu