Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285191008> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4285191008 endingPage "1363" @default.
- W4285191008 startingPage "1352" @default.
- W4285191008 abstract "Recently academia and industry has growing interest in the sixth generation network, which aims to support a rich range of applications with higher capacity and greater coverage than existing 5G connections. One of such promising applications that can benefit from 6G is Decentralised Federated Learning, a privacy-preserving machine learning paradigm. Also, it relies heavily on peer-to-peer mobile connection among edge and mobile devices, instead of a powerful central server on the cloud. However, the data and device heterogeneity, and highly dynamic environment in mobile networks pose challenges to the performance of federated learning. In this paper, we propose a data redistribution phase that balances the data distribution on different participating devices to a certain degree, which can further increase the system performance in the training phase. To derive our method, we first model this problem as a bargaining game, the equilibrium of which is formalised as an optimisation problem. Then we propose two algorithms to solve it: a centralised one, and a decentralised one that each participant executes without centralised coordination. We further improve the energy efficiency of the decentralised algorithm by introducing several heuristics. We evaluate the proposed system with both simulation and DNN training tasks on large scale FEMNIST-based datasets." @default.
- W4285191008 created "2022-07-14" @default.
- W4285191008 creator A5000529385 @default.
- W4285191008 creator A5008881554 @default.
- W4285191008 creator A5020218641 @default.
- W4285191008 creator A5039176528 @default.
- W4285191008 creator A5045851321 @default.
- W4285191008 creator A5062093738 @default.
- W4285191008 creator A5068908330 @default.
- W4285191008 creator A5072070557 @default.
- W4285191008 creator A5084238888 @default.
- W4285191008 date "2023-05-01" @default.
- W4285191008 modified "2023-10-18" @default.
- W4285191008 title "Energy-Efficient and Fair IoT Data Distribution in Decentralised Federated Learning" @default.
- W4285191008 cites W2017990047 @default.
- W4285191008 cites W2117905067 @default.
- W4285191008 cites W2623254152 @default.
- W4285191008 cites W2883271860 @default.
- W4285191008 cites W2955897898 @default.
- W4285191008 cites W2969077220 @default.
- W4285191008 cites W2993508366 @default.
- W4285191008 cites W3006360344 @default.
- W4285191008 cites W3014570036 @default.
- W4285191008 cites W3045747588 @default.
- W4285191008 cites W3047304572 @default.
- W4285191008 cites W3089875883 @default.
- W4285191008 cites W3091635927 @default.
- W4285191008 cites W3101718285 @default.
- W4285191008 cites W3102535235 @default.
- W4285191008 cites W3103448395 @default.
- W4285191008 cites W3127807476 @default.
- W4285191008 cites W3161501971 @default.
- W4285191008 cites W3176174985 @default.
- W4285191008 cites W3186051974 @default.
- W4285191008 cites W3197102448 @default.
- W4285191008 cites W3215554746 @default.
- W4285191008 cites W4240896209 @default.
- W4285191008 cites W4250589301 @default.
- W4285191008 doi "https://doi.org/10.1109/tnse.2022.3185672" @default.
- W4285191008 hasPublicationYear "2023" @default.
- W4285191008 type Work @default.
- W4285191008 citedByCount "0" @default.
- W4285191008 crossrefType "journal-article" @default.
- W4285191008 hasAuthorship W4285191008A5000529385 @default.
- W4285191008 hasAuthorship W4285191008A5008881554 @default.
- W4285191008 hasAuthorship W4285191008A5020218641 @default.
- W4285191008 hasAuthorship W4285191008A5039176528 @default.
- W4285191008 hasAuthorship W4285191008A5045851321 @default.
- W4285191008 hasAuthorship W4285191008A5062093738 @default.
- W4285191008 hasAuthorship W4285191008A5068908330 @default.
- W4285191008 hasAuthorship W4285191008A5072070557 @default.
- W4285191008 hasAuthorship W4285191008A5084238888 @default.
- W4285191008 hasConcept C111919701 @default.
- W4285191008 hasConcept C119599485 @default.
- W4285191008 hasConcept C120314980 @default.
- W4285191008 hasConcept C127413603 @default.
- W4285191008 hasConcept C127705205 @default.
- W4285191008 hasConcept C154945302 @default.
- W4285191008 hasConcept C2742236 @default.
- W4285191008 hasConcept C41008148 @default.
- W4285191008 hasConcept C79974875 @default.
- W4285191008 hasConceptScore W4285191008C111919701 @default.
- W4285191008 hasConceptScore W4285191008C119599485 @default.
- W4285191008 hasConceptScore W4285191008C120314980 @default.
- W4285191008 hasConceptScore W4285191008C127413603 @default.
- W4285191008 hasConceptScore W4285191008C127705205 @default.
- W4285191008 hasConceptScore W4285191008C154945302 @default.
- W4285191008 hasConceptScore W4285191008C2742236 @default.
- W4285191008 hasConceptScore W4285191008C41008148 @default.
- W4285191008 hasConceptScore W4285191008C79974875 @default.
- W4285191008 hasFunder F4320321001 @default.
- W4285191008 hasIssue "3" @default.
- W4285191008 hasLocation W42851910081 @default.
- W4285191008 hasOpenAccess W4285191008 @default.
- W4285191008 hasPrimaryLocation W42851910081 @default.
- W4285191008 hasRelatedWork W1987415113 @default.
- W4285191008 hasRelatedWork W1992885099 @default.
- W4285191008 hasRelatedWork W2109189940 @default.
- W4285191008 hasRelatedWork W2318636398 @default.
- W4285191008 hasRelatedWork W2383532021 @default.
- W4285191008 hasRelatedWork W2408491335 @default.
- W4285191008 hasRelatedWork W2546975154 @default.
- W4285191008 hasRelatedWork W2786808640 @default.
- W4285191008 hasRelatedWork W2884576438 @default.
- W4285191008 hasRelatedWork W3197929162 @default.
- W4285191008 hasVolume "10" @default.
- W4285191008 isParatext "false" @default.
- W4285191008 isRetracted "false" @default.
- W4285191008 workType "article" @default.