Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293143648> ?p ?o ?g. }
- W4293143648 endingPage "880" @default.
- W4293143648 startingPage "869" @default.
- W4293143648 abstract "Federated Learning (FL) is believed as a promising manner of distributed machine learning for 5G and future 6G networks in the context of mobile edge computing (MEC). From the worker’s viewpoint, a problem is that no incentive drives them to participate in FL. Thus, different from the conventional server-centric model allocation methods, we study the worker-centric strategy in this paper. Because communicating with the FL server and training an FL model locally are energy-hungry, a dilemma for each worker is how to make the tradeoff between participating in FL training and the volume restriction of its battery. To address this issue, we formulate a WorkerFirst problem. Its NP-hardness is also proved. Next, we devise a DDQN algorithm and a DQL algorithm to strive for near-optimal decisions for each worker. These two algorithms are proposed by leveraging the deep reinforcement learning framework, while considering the energy consumption, training timespan, and the communication overheads of workers, simultaneously. The benefit of adopting such a DRL-based decision-making framework is that workers can execute the algorithms locally and dynamically adapt to the varying MEC environment. The evaluation results show that the proposed DDQN and DQL algorithms can learn good policies without knowing any prior knowledge of network conditions." @default.
- W4293143648 created "2022-08-27" @default.
- W4293143648 creator A5012731436 @default.
- W4293143648 creator A5047931252 @default.
- W4293143648 creator A5049692788 @default.
- W4293143648 creator A5054645292 @default.
- W4293143648 date "2023-06-01" @default.
- W4293143648 modified "2023-10-11" @default.
- W4293143648 title "Worker-Centric Model Allocation for Federated Learning in Mobile Edge Computing" @default.
- W4293143648 cites W1972300623 @default.
- W4293143648 cites W2001027366 @default.
- W4293143648 cites W2064036620 @default.
- W4293143648 cites W2095356712 @default.
- W4293143648 cites W2118588134 @default.
- W4293143648 cites W2145339207 @default.
- W4293143648 cites W2624989916 @default.
- W4293143648 cites W2746553466 @default.
- W4293143648 cites W2777180355 @default.
- W4293143648 cites W2786070938 @default.
- W4293143648 cites W2907638403 @default.
- W4293143648 cites W2920095265 @default.
- W4293143648 cites W2938135176 @default.
- W4293143648 cites W2962856838 @default.
- W4293143648 cites W2982628788 @default.
- W4293143648 cites W3000385461 @default.
- W4293143648 cites W3006403513 @default.
- W4293143648 cites W3015636663 @default.
- W4293143648 cites W3023574229 @default.
- W4293143648 cites W3090984959 @default.
- W4293143648 cites W3095611529 @default.
- W4293143648 cites W3101718285 @default.
- W4293143648 cites W3103802018 @default.
- W4293143648 cites W3104572184 @default.
- W4293143648 cites W3105122387 @default.
- W4293143648 cites W3124943657 @default.
- W4293143648 cites W3127049675 @default.
- W4293143648 cites W3138166792 @default.
- W4293143648 cites W3163279171 @default.
- W4293143648 cites W3213120752 @default.
- W4293143648 cites W4255535209 @default.
- W4293143648 cites W4313153564 @default.
- W4293143648 doi "https://doi.org/10.1109/tgcn.2022.3187335" @default.
- W4293143648 hasPublicationYear "2023" @default.
- W4293143648 type Work @default.
- W4293143648 citedByCount "0" @default.
- W4293143648 crossrefType "journal-article" @default.
- W4293143648 hasAuthorship W4293143648A5012731436 @default.
- W4293143648 hasAuthorship W4293143648A5047931252 @default.
- W4293143648 hasAuthorship W4293143648A5049692788 @default.
- W4293143648 hasAuthorship W4293143648A5054645292 @default.
- W4293143648 hasConcept C111472728 @default.
- W4293143648 hasConcept C111919701 @default.
- W4293143648 hasConcept C119857082 @default.
- W4293143648 hasConcept C120314980 @default.
- W4293143648 hasConcept C138236772 @default.
- W4293143648 hasConcept C138885662 @default.
- W4293143648 hasConcept C151730666 @default.
- W4293143648 hasConcept C154945302 @default.
- W4293143648 hasConcept C162307627 @default.
- W4293143648 hasConcept C162324750 @default.
- W4293143648 hasConcept C175444787 @default.
- W4293143648 hasConcept C18903297 @default.
- W4293143648 hasConcept C2776061582 @default.
- W4293143648 hasConcept C2778496695 @default.
- W4293143648 hasConcept C2779343474 @default.
- W4293143648 hasConcept C2780165032 @default.
- W4293143648 hasConcept C29122968 @default.
- W4293143648 hasConcept C41008148 @default.
- W4293143648 hasConcept C79974875 @default.
- W4293143648 hasConcept C86803240 @default.
- W4293143648 hasConcept C97541855 @default.
- W4293143648 hasConceptScore W4293143648C111472728 @default.
- W4293143648 hasConceptScore W4293143648C111919701 @default.
- W4293143648 hasConceptScore W4293143648C119857082 @default.
- W4293143648 hasConceptScore W4293143648C120314980 @default.
- W4293143648 hasConceptScore W4293143648C138236772 @default.
- W4293143648 hasConceptScore W4293143648C138885662 @default.
- W4293143648 hasConceptScore W4293143648C151730666 @default.
- W4293143648 hasConceptScore W4293143648C154945302 @default.
- W4293143648 hasConceptScore W4293143648C162307627 @default.
- W4293143648 hasConceptScore W4293143648C162324750 @default.
- W4293143648 hasConceptScore W4293143648C175444787 @default.
- W4293143648 hasConceptScore W4293143648C18903297 @default.
- W4293143648 hasConceptScore W4293143648C2776061582 @default.
- W4293143648 hasConceptScore W4293143648C2778496695 @default.
- W4293143648 hasConceptScore W4293143648C2779343474 @default.
- W4293143648 hasConceptScore W4293143648C2780165032 @default.
- W4293143648 hasConceptScore W4293143648C29122968 @default.
- W4293143648 hasConceptScore W4293143648C41008148 @default.
- W4293143648 hasConceptScore W4293143648C79974875 @default.
- W4293143648 hasConceptScore W4293143648C86803240 @default.
- W4293143648 hasConceptScore W4293143648C97541855 @default.
- W4293143648 hasFunder F4320321001 @default.
- W4293143648 hasFunder F4320335777 @default.
- W4293143648 hasFunder F4320337111 @default.
- W4293143648 hasIssue "2" @default.
- W4293143648 hasLocation W42931436481 @default.
- W4293143648 hasOpenAccess W4293143648 @default.