Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090253162> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3090253162 abstract "This paper proposes a client selection method for federated learning (FL) when the computation and communication resource of clients cannot be estimated; the method trains a machine learning (ML) model using the rich data and computational resources of mobile clients without collecting their data in central systems. Conventional FL with client selection estimates the required time for an FL round from a given clients' computation power and throughput and determines a client set to reduce time consumption in FL rounds. However, it is difficult to obtain accurate resource information for all clients before the FL process is conducted because the available computation and communication resources change easily based on background computation tasks, background traffic, bottleneck links, etc. Consequently, the FL operator must select clients through exploration and exploitation processes. This paper proposes a multi-armed bandit (MAB)-based client selection method to solve the exploration and exploitation trade-off and reduce the time consumption for FL in mobile networks. The proposed method balances the selection of clients for which the amount of resources is uncertain and those known to have a large amount of resources. The simulation evaluation demonstrated that the proposed scheme requires less learning time than the conventional method in the resource fluctuating scenario." @default.
- W3090253162 created "2020-10-08" @default.
- W3090253162 creator A5042195263 @default.
- W3090253162 creator A5043357764 @default.
- W3090253162 creator A5063642951 @default.
- W3090253162 creator A5084734266 @default.
- W3090253162 date "2020-09-29" @default.
- W3090253162 modified "2023-10-16" @default.
- W3090253162 title "MAB-based Client Selection for Federated Learning with Uncertain Resources in Mobile Networks" @default.
- W3090253162 cites W1490674876 @default.
- W3090253162 cites W1991056455 @default.
- W3090253162 cites W2168405694 @default.
- W3090253162 cites W2535838896 @default.
- W3090253162 cites W2541884796 @default.
- W3090253162 cites W2807006176 @default.
- W3090253162 cites W2913570153 @default.
- W3090253162 cites W2963803379 @default.
- W3090253162 cites W2974393504 @default.
- W3090253162 cites W2986511432 @default.
- W3090253162 cites W3015574552 @default.
- W3090253162 cites W3045747588 @default.
- W3090253162 cites W3105122387 @default.
- W3090253162 cites W3118608800 @default.
- W3090253162 doi "https://doi.org/10.48550/arxiv.2009.13879" @default.
- W3090253162 hasPublicationYear "2020" @default.
- W3090253162 type Work @default.
- W3090253162 sameAs 3090253162 @default.
- W3090253162 citedByCount "0" @default.
- W3090253162 crossrefType "posted-content" @default.
- W3090253162 hasAuthorship W3090253162A5042195263 @default.
- W3090253162 hasAuthorship W3090253162A5043357764 @default.
- W3090253162 hasAuthorship W3090253162A5063642951 @default.
- W3090253162 hasAuthorship W3090253162A5084734266 @default.
- W3090253162 hasBestOaLocation W30902531621 @default.
- W3090253162 hasConcept C111919701 @default.
- W3090253162 hasConcept C11413529 @default.
- W3090253162 hasConcept C119857082 @default.
- W3090253162 hasConcept C120314980 @default.
- W3090253162 hasConcept C149635348 @default.
- W3090253162 hasConcept C157764524 @default.
- W3090253162 hasConcept C177264268 @default.
- W3090253162 hasConcept C190839683 @default.
- W3090253162 hasConcept C199360897 @default.
- W3090253162 hasConcept C205649164 @default.
- W3090253162 hasConcept C206345919 @default.
- W3090253162 hasConcept C2775973920 @default.
- W3090253162 hasConcept C2779960059 @default.
- W3090253162 hasConcept C2780513914 @default.
- W3090253162 hasConcept C31258907 @default.
- W3090253162 hasConcept C41008148 @default.
- W3090253162 hasConcept C45374587 @default.
- W3090253162 hasConcept C555944384 @default.
- W3090253162 hasConcept C58640448 @default.
- W3090253162 hasConcept C76155785 @default.
- W3090253162 hasConcept C81917197 @default.
- W3090253162 hasConcept C98045186 @default.
- W3090253162 hasConceptScore W3090253162C111919701 @default.
- W3090253162 hasConceptScore W3090253162C11413529 @default.
- W3090253162 hasConceptScore W3090253162C119857082 @default.
- W3090253162 hasConceptScore W3090253162C120314980 @default.
- W3090253162 hasConceptScore W3090253162C149635348 @default.
- W3090253162 hasConceptScore W3090253162C157764524 @default.
- W3090253162 hasConceptScore W3090253162C177264268 @default.
- W3090253162 hasConceptScore W3090253162C190839683 @default.
- W3090253162 hasConceptScore W3090253162C199360897 @default.
- W3090253162 hasConceptScore W3090253162C205649164 @default.
- W3090253162 hasConceptScore W3090253162C206345919 @default.
- W3090253162 hasConceptScore W3090253162C2775973920 @default.
- W3090253162 hasConceptScore W3090253162C2779960059 @default.
- W3090253162 hasConceptScore W3090253162C2780513914 @default.
- W3090253162 hasConceptScore W3090253162C31258907 @default.
- W3090253162 hasConceptScore W3090253162C41008148 @default.
- W3090253162 hasConceptScore W3090253162C45374587 @default.
- W3090253162 hasConceptScore W3090253162C555944384 @default.
- W3090253162 hasConceptScore W3090253162C58640448 @default.
- W3090253162 hasConceptScore W3090253162C76155785 @default.
- W3090253162 hasConceptScore W3090253162C81917197 @default.
- W3090253162 hasConceptScore W3090253162C98045186 @default.
- W3090253162 hasLocation W30902531621 @default.
- W3090253162 hasOpenAccess W3090253162 @default.
- W3090253162 hasPrimaryLocation W30902531621 @default.
- W3090253162 hasRelatedWork W1597592026 @default.
- W3090253162 hasRelatedWork W1998323989 @default.
- W3090253162 hasRelatedWork W2124870959 @default.
- W3090253162 hasRelatedWork W2157013742 @default.
- W3090253162 hasRelatedWork W2391167130 @default.
- W3090253162 hasRelatedWork W2773549774 @default.
- W3090253162 hasRelatedWork W3131271896 @default.
- W3090253162 hasRelatedWork W4283067488 @default.
- W3090253162 hasRelatedWork W94000989 @default.
- W3090253162 hasRelatedWork W2516240846 @default.
- W3090253162 isParatext "false" @default.
- W3090253162 isRetracted "false" @default.
- W3090253162 magId "3090253162" @default.
- W3090253162 workType "article" @default.