FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311454612> ?p ?o ?g. }

• W4311454612 endingPage "109517" @default.
• W4311454612 startingPage "109517" @default.
• W4311454612 abstract "A fundamental issue for federated learning (FL) is how to achieve efficient training performance under complex dynamic communication environments. This issue can be alleviated by the fact that modern edge devices usually can connect to the edge server via multiple communication channels (e.g., 4G, LTE, and 5G) because multi-channel communication can increase the communication bandwidth and has lower communication costs and energy consumption than a single high-speed communication channel. However, if the communication data cannot be properly allocated to multiple channels in a complex dynamic communication network, multi-channel communication will still waste resources (e.g., bandwidth, battery life, and monetary cost). In this paper, we propose an efficient FL framework called, which consists of two parts, the layered gradient compression (LGC), and a learning-driven control algorithm. Specifically, with LGC, local gradients from a device are coded into several layers, and each layer is sent to the server along a different channel. The FL server aggregates the received layers of local gradients from devices to update the global model and sends the result back to the devices. Furthermore, we prove the convergence of LGC and formally define the problem of resource-efficient with LGC. We then propose a learning-driven algorithm for each device to dynamically adjust its local computation (i.e., the number of local stochastic descent) and communication decisions (i.e., the compression level of different layers and the layer-to-channel mapping) in each iteration. Results from extensive experiments show that significantly reduces the training time and improves the resource utilization (energy consumption and money cost) while achieving a similar test accuracy compared with well-known FL baselines." @default.
• W4311454612 created "2022-12-26" @default.
• W4311454612 creator A5015404751 @default.
• W4311454612 creator A5028781275 @default.
• W4311454612 creator A5037049308 @default.
• W4311454612 creator A5079286251 @default.
• W4311454612 creator A5084768325 @default.
• W4311454612 date "2023-02-01" @default.
• W4311454612 modified "2023-10-13" @default.
• W4311454612 title "An efficient federated learning framework for multi-channeled mobile edge network with layered gradient compression" @default.
• W4311454612 cites W2064675550 @default.
• W4311454612 cites W2112796928 @default.
• W4311454612 cites W2145339207 @default.
• W4311454612 cites W2405578611 @default.
• W4311454612 cites W2407022425 @default.
• W4311454612 cites W2498119267 @default.
• W4311454612 cites W2546571074 @default.
• W4311454612 cites W2746553466 @default.
• W4311454612 cites W2775776326 @default.
• W4311454612 cites W2912213068 @default.
• W4311454612 cites W2922260520 @default.
• W4311454612 cites W2962788286 @default.
• W4311454612 cites W2962804345 @default.
• W4311454612 cites W2962952793 @default.
• W4311454612 cites W2963318081 @default.
• W4311454612 cites W2999074226 @default.
• W4311454612 cites W3006919779 @default.
• W4311454612 cites W3043758338 @default.
• W4311454612 cites W3087704775 @default.
• W4311454612 cites W3090615085 @default.
• W4311454612 cites W3101036738 @default.
• W4311454612 cites W3111182214 @default.
• W4311454612 cites W3198696615 @default.
• W4311454612 cites W3205260830 @default.
• W4311454612 cites W4226263557 @default.
• W4311454612 doi "https://doi.org/10.1016/j.comnet.2022.109517" @default.
• W4311454612 hasPublicationYear "2023" @default.
• W4311454612 type Work @default.
• W4311454612 citedByCount "0" @default.
• W4311454612 crossrefType "journal-article" @default.
• W4311454612 hasAuthorship W4311454612A5015404751 @default.
• W4311454612 hasAuthorship W4311454612A5028781275 @default.
• W4311454612 hasAuthorship W4311454612A5037049308 @default.
• W4311454612 hasAuthorship W4311454612A5079286251 @default.
• W4311454612 hasAuthorship W4311454612A5084768325 @default.
• W4311454612 hasConcept C101765175 @default.
• W4311454612 hasConcept C111919701 @default.
• W4311454612 hasConcept C11413529 @default.
• W4311454612 hasConcept C120314980 @default.
• W4311454612 hasConcept C127162648 @default.
• W4311454612 hasConcept C138236772 @default.
• W4311454612 hasConcept C154945302 @default.
• W4311454612 hasConcept C162307627 @default.
• W4311454612 hasConcept C178790620 @default.
• W4311454612 hasConcept C185592680 @default.
• W4311454612 hasConcept C186967261 @default.
• W4311454612 hasConcept C2776257435 @default.
• W4311454612 hasConcept C2779227376 @default.
• W4311454612 hasConcept C31258907 @default.
• W4311454612 hasConcept C41008148 @default.
• W4311454612 hasConcept C45374587 @default.
• W4311454612 hasConcept C79974875 @default.
• W4311454612 hasConceptScore W4311454612C101765175 @default.
• W4311454612 hasConceptScore W4311454612C111919701 @default.
• W4311454612 hasConceptScore W4311454612C11413529 @default.
• W4311454612 hasConceptScore W4311454612C120314980 @default.
• W4311454612 hasConceptScore W4311454612C127162648 @default.
• W4311454612 hasConceptScore W4311454612C138236772 @default.
• W4311454612 hasConceptScore W4311454612C154945302 @default.
• W4311454612 hasConceptScore W4311454612C162307627 @default.
• W4311454612 hasConceptScore W4311454612C178790620 @default.
• W4311454612 hasConceptScore W4311454612C185592680 @default.
• W4311454612 hasConceptScore W4311454612C186967261 @default.
• W4311454612 hasConceptScore W4311454612C2776257435 @default.
• W4311454612 hasConceptScore W4311454612C2779227376 @default.
• W4311454612 hasConceptScore W4311454612C31258907 @default.
• W4311454612 hasConceptScore W4311454612C41008148 @default.
• W4311454612 hasConceptScore W4311454612C45374587 @default.
• W4311454612 hasConceptScore W4311454612C79974875 @default.
• W4311454612 hasFunder F4320321001 @default.
• W4311454612 hasLocation W43114546121 @default.
• W4311454612 hasOpenAccess W4311454612 @default.
• W4311454612 hasPrimaryLocation W43114546121 @default.
• W4311454612 hasRelatedWork W2793906774 @default.
• W4311454612 hasRelatedWork W2900070427 @default.
• W4311454612 hasRelatedWork W3046945740 @default.
• W4311454612 hasRelatedWork W3140014003 @default.
• W4311454612 hasRelatedWork W4311454612 @default.
• W4311454612 hasRelatedWork W4312306383 @default.
• W4311454612 hasRelatedWork W4313656027 @default.
• W4311454612 hasRelatedWork W4324368142 @default.
• W4311454612 hasRelatedWork W4376106090 @default.
• W4311454612 hasRelatedWork W2805391225 @default.
• W4311454612 hasVolume "221" @default.
• W4311454612 isParatext "false" @default.
• W4311454612 isRetracted "false" @default.
• W4311454612 workType "article" @default.