FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4320009767> ?p ?o ?g. }

• W4320009767 endingPage "10856" @default.
• W4320009767 startingPage "10845" @default.
• W4320009767 abstract "Low latency, resource efficiency, and data privacy are some of the crucial requirements in modern communication networks. Federated learning can efficiently address these issues by utilizing the data at the network edge and processing massive amounts of data in parallel at the edge devices, thus ensuring data privacy and low latency. For a large-scale federated learning task spanning many devices, challenges arise due to device heterogeneity, data variability, and limited network resources. Optimal selection of edge devices participating in federated learning is essential to attaining resilient, reliable, and resource-efficient edge networks. In this context, this article proposes an optimal device selection method to minimize redundant data training and improve network resource utilization without affecting the performance of federated learning over resource-constrained edge networks. The proposed optimal device selection method aims to minimize network resource demands while maximizing data diversity within the aggregated model. The performance of the proposed federated learning framework is evaluated using a publicly available image data set of handwritten digits, EMNIST (an extended version of the MNIST data set). Experimental results indicate that the proposed framework can obtain accuracy convergence performance on par with conventional federated learning methods while significantly reducing device usage (up to <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$50%$ </tex-math></inline-formula> ) and resource utilization (up to <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$30%$ </tex-math></inline-formula> ) while reaching 99% of achievable accuracy. The proposed method can therefore be effectively applied to resource-constrained edge networks." @default.
• W4320009767 created "2023-02-11" @default.
• W4320009767 creator A5020399355 @default.
• W4320009767 creator A5029995536 @default.
• W4320009767 creator A5033168903 @default.
• W4320009767 creator A5085503354 @default.
• W4320009767 date "2023-06-15" @default.
• W4320009767 modified "2023-10-16" @default.
• W4320009767 title "Optimal Device Selection in Federated Learning for Resource-Constrained Edge Networks" @default.
• W4320009767 cites W2734358244 @default.
• W4320009767 cites W2896422817 @default.
• W4320009767 cites W2912213068 @default.
• W4320009767 cites W2915771847 @default.
• W4320009767 cites W2989289980 @default.
• W4320009767 cites W2991236681 @default.
• W4320009767 cites W3015636663 @default.
• W4320009767 cites W3045638580 @default.
• W4320009767 cites W3095611529 @default.
• W4320009767 cites W3101073882 @default.
• W4320009767 cites W3102496129 @default.
• W4320009767 cites W3103802018 @default.
• W4320009767 cites W3105122387 @default.
• W4320009767 cites W3113075536 @default.
• W4320009767 cites W3128382687 @default.
• W4320009767 cites W3131195871 @default.
• W4320009767 cites W3131500902 @default.
• W4320009767 cites W3131796779 @default.
• W4320009767 cites W3155160971 @default.
• W4320009767 cites W3155963862 @default.
• W4320009767 cites W3156953231 @default.
• W4320009767 cites W3177095755 @default.
• W4320009767 cites W3184192107 @default.
• W4320009767 cites W4287218656 @default.
• W4320009767 doi "https://doi.org/10.1109/jiot.2023.3243082" @default.
• W4320009767 hasPublicationYear "2023" @default.
• W4320009767 type Work @default.
• W4320009767 citedByCount "0" @default.
• W4320009767 crossrefType "journal-article" @default.
• W4320009767 hasAuthorship W4320009767A5020399355 @default.
• W4320009767 hasAuthorship W4320009767A5029995536 @default.
• W4320009767 hasAuthorship W4320009767A5033168903 @default.
• W4320009767 hasAuthorship W4320009767A5085503354 @default.
• W4320009767 hasConcept C108583219 @default.
• W4320009767 hasConcept C111919701 @default.
• W4320009767 hasConcept C119857082 @default.
• W4320009767 hasConcept C120314980 @default.
• W4320009767 hasConcept C124101348 @default.
• W4320009767 hasConcept C138236772 @default.
• W4320009767 hasConcept C151730666 @default.
• W4320009767 hasConcept C154945302 @default.
• W4320009767 hasConcept C162307627 @default.
• W4320009767 hasConcept C190502265 @default.
• W4320009767 hasConcept C206345919 @default.
• W4320009767 hasConcept C2779343474 @default.
• W4320009767 hasConcept C31258907 @default.
• W4320009767 hasConcept C41008148 @default.
• W4320009767 hasConcept C76155785 @default.
• W4320009767 hasConcept C79974875 @default.
• W4320009767 hasConcept C81917197 @default.
• W4320009767 hasConcept C82876162 @default.
• W4320009767 hasConcept C86803240 @default.
• W4320009767 hasConceptScore W4320009767C108583219 @default.
• W4320009767 hasConceptScore W4320009767C111919701 @default.
• W4320009767 hasConceptScore W4320009767C119857082 @default.
• W4320009767 hasConceptScore W4320009767C120314980 @default.
• W4320009767 hasConceptScore W4320009767C124101348 @default.
• W4320009767 hasConceptScore W4320009767C138236772 @default.
• W4320009767 hasConceptScore W4320009767C151730666 @default.
• W4320009767 hasConceptScore W4320009767C154945302 @default.
• W4320009767 hasConceptScore W4320009767C162307627 @default.
• W4320009767 hasConceptScore W4320009767C190502265 @default.
• W4320009767 hasConceptScore W4320009767C206345919 @default.
• W4320009767 hasConceptScore W4320009767C2779343474 @default.
• W4320009767 hasConceptScore W4320009767C31258907 @default.
• W4320009767 hasConceptScore W4320009767C41008148 @default.
• W4320009767 hasConceptScore W4320009767C76155785 @default.
• W4320009767 hasConceptScore W4320009767C79974875 @default.
• W4320009767 hasConceptScore W4320009767C81917197 @default.
• W4320009767 hasConceptScore W4320009767C82876162 @default.
• W4320009767 hasConceptScore W4320009767C86803240 @default.
• W4320009767 hasFunder F4320306076 @default.
• W4320009767 hasFunder F4320337345 @default.
• W4320009767 hasIssue "12" @default.
• W4320009767 hasLocation W43200097671 @default.
• W4320009767 hasOpenAccess W4320009767 @default.
• W4320009767 hasPrimaryLocation W43200097671 @default.
• W4320009767 hasRelatedWork W2298102683 @default.
• W4320009767 hasRelatedWork W2597787948 @default.
• W4320009767 hasRelatedWork W2982829524 @default.
• W4320009767 hasRelatedWork W3176734149 @default.
• W4320009767 hasRelatedWork W4281678247 @default.
• W4320009767 hasRelatedWork W4293869292 @default.
• W4320009767 hasRelatedWork W4313339048 @default.
• W4320009767 hasRelatedWork W4376106090 @default.
• W4320009767 hasRelatedWork W4386262998 @default.
• W4320009767 hasRelatedWork W3129097341 @default.
• W4320009767 hasVolume "10" @default.
• W4320009767 isParatext "false" @default.

• next