Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381248061> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4381248061 abstract "In 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. 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. 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 F1 scores 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." @default.
- W4381248061 created "2023-06-20" @default.
- W4381248061 creator A5028566199 @default.
- W4381248061 creator A5033414840 @default.
- W4381248061 creator A5049029315 @default.
- W4381248061 creator A5059796926 @default.
- W4381248061 creator A5063531116 @default.
- W4381248061 creator A5068451806 @default.
- W4381248061 creator A5070889566 @default.
- W4381248061 creator A5076837396 @default.
- W4381248061 creator A5089156582 @default.
- W4381248061 date "2023-06-16" @default.
- W4381248061 modified "2023-10-16" @default.
- W4381248061 title "Fedstellar: A Platform for Decentralized Federated Learning" @default.
- W4381248061 doi "https://doi.org/10.48550/arxiv.2306.09750" @default.
- W4381248061 hasPublicationYear "2023" @default.
- W4381248061 type Work @default.
- W4381248061 citedByCount "0" @default.
- W4381248061 crossrefType "posted-content" @default.
- W4381248061 hasAuthorship W4381248061A5028566199 @default.
- W4381248061 hasAuthorship W4381248061A5033414840 @default.
- W4381248061 hasAuthorship W4381248061A5049029315 @default.
- W4381248061 hasAuthorship W4381248061A5059796926 @default.
- W4381248061 hasAuthorship W4381248061A5063531116 @default.
- W4381248061 hasAuthorship W4381248061A5068451806 @default.
- W4381248061 hasAuthorship W4381248061A5070889566 @default.
- W4381248061 hasAuthorship W4381248061A5076837396 @default.
- W4381248061 hasAuthorship W4381248061A5089156582 @default.
- W4381248061 hasBestOaLocation W43812480611 @default.
- W4381248061 hasConcept C105339364 @default.
- W4381248061 hasConcept C108583219 @default.
- W4381248061 hasConcept C115903868 @default.
- W4381248061 hasConcept C120314980 @default.
- W4381248061 hasConcept C154945302 @default.
- W4381248061 hasConcept C159985019 @default.
- W4381248061 hasConcept C165136773 @default.
- W4381248061 hasConcept C177606310 @default.
- W4381248061 hasConcept C18903297 @default.
- W4381248061 hasConcept C190502265 @default.
- W4381248061 hasConcept C192562407 @default.
- W4381248061 hasConcept C199845137 @default.
- W4381248061 hasConcept C26517878 @default.
- W4381248061 hasConcept C31258907 @default.
- W4381248061 hasConcept C38652104 @default.
- W4381248061 hasConcept C41008148 @default.
- W4381248061 hasConcept C4679612 @default.
- W4381248061 hasConcept C86803240 @default.
- W4381248061 hasConcept C93996380 @default.
- W4381248061 hasConceptScore W4381248061C105339364 @default.
- W4381248061 hasConceptScore W4381248061C108583219 @default.
- W4381248061 hasConceptScore W4381248061C115903868 @default.
- W4381248061 hasConceptScore W4381248061C120314980 @default.
- W4381248061 hasConceptScore W4381248061C154945302 @default.
- W4381248061 hasConceptScore W4381248061C159985019 @default.
- W4381248061 hasConceptScore W4381248061C165136773 @default.
- W4381248061 hasConceptScore W4381248061C177606310 @default.
- W4381248061 hasConceptScore W4381248061C18903297 @default.
- W4381248061 hasConceptScore W4381248061C190502265 @default.
- W4381248061 hasConceptScore W4381248061C192562407 @default.
- W4381248061 hasConceptScore W4381248061C199845137 @default.
- W4381248061 hasConceptScore W4381248061C26517878 @default.
- W4381248061 hasConceptScore W4381248061C31258907 @default.
- W4381248061 hasConceptScore W4381248061C38652104 @default.
- W4381248061 hasConceptScore W4381248061C41008148 @default.
- W4381248061 hasConceptScore W4381248061C4679612 @default.
- W4381248061 hasConceptScore W4381248061C86803240 @default.
- W4381248061 hasConceptScore W4381248061C93996380 @default.
- W4381248061 hasLocation W43812480611 @default.
- W4381248061 hasOpenAccess W4381248061 @default.
- W4381248061 hasPrimaryLocation W43812480611 @default.
- W4381248061 hasRelatedWork W1536804125 @default.
- W4381248061 hasRelatedWork W1543783347 @default.
- W4381248061 hasRelatedWork W1597592026 @default.
- W4381248061 hasRelatedWork W1651247419 @default.
- W4381248061 hasRelatedWork W2116178420 @default.
- W4381248061 hasRelatedWork W2170649215 @default.
- W4381248061 hasRelatedWork W2385763152 @default.
- W4381248061 hasRelatedWork W2469564240 @default.
- W4381248061 hasRelatedWork W2901029117 @default.
- W4381248061 hasRelatedWork W2909452277 @default.
- W4381248061 isParatext "false" @default.
- W4381248061 isRetracted "false" @default.
- W4381248061 workType "article" @default.