FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283714314> ?p ?o ?g. }

• W4283714314 endingPage "280" @default.
• W4283714314 startingPage "265" @default.
• W4283714314 abstract "The aim of this paper is to propose a novel dynamic resource allocation strategy for energy-efficient adaptive federated learning at the wireless network edge, with latency and learning performance guarantees. We consider a set of devices collecting local data and uploading processed information to an edge server, which runs stochastic gradient-based algorithms to perform continuous learning and adaptation. Hinging on Lyapunov stochastic optimization tools, we dynamically optimize radio parameters (e.g., set of transmitting devices, transmit powers, bits, and rates) and computation resources (e.g., CPU cycles at devices and at server) in order to strike the best trade-off between power, latency, and performance of the federated learning task. The framework admits both a model-based implementation, where the learning performance metrics are available in closed-form, and a data-driven approach, which works with online estimates of the learning performance of interest. The method is then customized to the case of federated least mean squares (LMS) estimation, and federated training of deep convolutional neural networks. Numerical results illustrate the effectiveness of our strategy to perform energy-efficient, low-latency, adaptive federated learning at the wireless network edge." @default.
• W4283714314 created "2022-07-01" @default.
• W4283714314 creator A5000852147 @default.
• W4283714314 creator A5007993461 @default.
• W4283714314 creator A5062501594 @default.
• W4283714314 creator A5084159640 @default.
• W4283714314 date "2023-03-01" @default.
• W4283714314 modified "2023-10-05" @default.
• W4283714314 title "Lyapunov-Based Optimization of Edge Resources for Energy-Efficient Adaptive Federated Learning" @default.
• W4283714314 cites W2001027366 @default.
• W4283714314 cites W2082011829 @default.
• W4283714314 cites W2112796928 @default.
• W4283714314 cites W2151007095 @default.
• W4283714314 cites W2170746474 @default.
• W4283714314 cites W2883059862 @default.
• W4283714314 cites W2920095265 @default.
• W4283714314 cites W2960833983 @default.
• W4283714314 cites W2962716476 @default.
• W4283714314 cites W2962766183 @default.
• W4283714314 cites W2962814013 @default.
• W4283714314 cites W2963318081 @default.
• W4283714314 cites W2969077220 @default.
• W4283714314 cites W2975156709 @default.
• W4283714314 cites W2975802305 @default.
• W4283714314 cites W2979359324 @default.
• W4283714314 cites W2991236681 @default.
• W4283714314 cites W3010717392 @default.
• W4283714314 cites W3014208382 @default.
• W4283714314 cites W3015613093 @default.
• W4283714314 cites W3016207298 @default.
• W4283714314 cites W3045027907 @default.
• W4283714314 cites W3045657448 @default.
• W4283714314 cites W3089655738 @default.
• W4283714314 cites W3090615085 @default.
• W4283714314 cites W3095611529 @default.
• W4283714314 cites W3103072945 @default.
• W4283714314 cites W3103802018 @default.
• W4283714314 cites W3108383389 @default.
• W4283714314 cites W3109504587 @default.
• W4283714314 cites W3109847748 @default.
• W4283714314 cites W3111182214 @default.
• W4283714314 cites W3147370375 @default.
• W4283714314 cites W3161745778 @default.
• W4283714314 cites W3162353295 @default.
• W4283714314 cites W3178176830 @default.
• W4283714314 cites W3184442399 @default.
• W4283714314 cites W3207233526 @default.
• W4283714314 cites W3214304699 @default.
• W4283714314 cites W3214330255 @default.
• W4283714314 cites W4205987271 @default.
• W4283714314 cites W4301852635 @default.
• W4283714314 doi "https://doi.org/10.1109/tgcn.2022.3186879" @default.
• W4283714314 hasPublicationYear "2023" @default.
• W4283714314 type Work @default.
• W4283714314 citedByCount "3" @default.
• W4283714314 countsByYear W42837143142023 @default.
• W4283714314 crossrefType "journal-article" @default.
• W4283714314 hasAuthorship W4283714314A5000852147 @default.
• W4283714314 hasAuthorship W4283714314A5007993461 @default.
• W4283714314 hasAuthorship W4283714314A5062501594 @default.
• W4283714314 hasAuthorship W4283714314A5084159640 @default.
• W4283714314 hasBestOaLocation W42837143142 @default.
• W4283714314 hasConcept C101403955 @default.
• W4283714314 hasConcept C108583219 @default.
• W4283714314 hasConcept C111919701 @default.
• W4283714314 hasConcept C11413529 @default.
• W4283714314 hasConcept C120314980 @default.
• W4283714314 hasConcept C137836250 @default.
• W4283714314 hasConcept C138236772 @default.
• W4283714314 hasConcept C149672232 @default.
• W4283714314 hasConcept C154945302 @default.
• W4283714314 hasConcept C162307627 @default.
• W4283714314 hasConcept C191544260 @default.
• W4283714314 hasConcept C206688291 @default.
• W4283714314 hasConcept C2777052490 @default.
• W4283714314 hasConcept C2778456923 @default.
• W4283714314 hasConcept C37935115 @default.
• W4283714314 hasConcept C41008148 @default.
• W4283714314 hasConcept C50644808 @default.
• W4283714314 hasConcept C71901391 @default.
• W4283714314 hasConcept C76155785 @default.
• W4283714314 hasConcept C79403827 @default.
• W4283714314 hasConcept C79974875 @default.
• W4283714314 hasConcept C82876162 @default.
• W4283714314 hasConceptScore W4283714314C101403955 @default.
• W4283714314 hasConceptScore W4283714314C108583219 @default.
• W4283714314 hasConceptScore W4283714314C111919701 @default.
• W4283714314 hasConceptScore W4283714314C11413529 @default.
• W4283714314 hasConceptScore W4283714314C120314980 @default.
• W4283714314 hasConceptScore W4283714314C137836250 @default.
• W4283714314 hasConceptScore W4283714314C138236772 @default.
• W4283714314 hasConceptScore W4283714314C149672232 @default.
• W4283714314 hasConceptScore W4283714314C154945302 @default.
• W4283714314 hasConceptScore W4283714314C162307627 @default.
• W4283714314 hasConceptScore W4283714314C191544260 @default.
• W4283714314 hasConceptScore W4283714314C206688291 @default.
• W4283714314 hasConceptScore W4283714314C2777052490 @default.
• W4283714314 hasConceptScore W4283714314C2778456923 @default.

• next