Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317496738> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4317496738 endingPage "10306" @default.
- W4317496738 startingPage "10291" @default.
- W4317496738 abstract "Centralized learning now faces data mapping and security constraints that make it difficult to carry out. Federated learning with a distributed learning architecture has changed this situation. By restricting the training process to participants’ local, federated learning addresses the model training needs of multiple data sources while better protecting data privacy. However, in real-world application scenarios, federated learning faces the need to achieve fairness in addition to privacy protection. In practice, it could happen that some federated learning participants with specific motives may short join the training process to obtain the current global model with only limited contribution to the federated learning whole, resulting in unfairness to the participants who previously participated in federated learning. We propose the FedACC framework with a server-initiated global model accuracy control method to address this issue. Besides measuring the accumulative contributions of newly joined participants and providing participants with a model with an accuracy that matches their contributions, the FedACC still guarantees the validity of participant gradients based on the accuracy-decayed model. Under the FedACC framework, users do not have access to the full version of the current global model early in their training participation. However, they must produce a certain amount of contributions before seeing the full-accuracy model. We introduce an additional differential privacy mechanism to protect clients’ privacy further. Experiments demonstrate that the FedACC could obtain about 10%–20% accuracy gain compared to the state-of-the-art methods while balancing the fairness, performance, and security of federated learning." @default.
- W4317496738 created "2023-01-20" @default.
- W4317496738 creator A5001657111 @default.
- W4317496738 creator A5034637087 @default.
- W4317496738 creator A5052779809 @default.
- W4317496738 creator A5052928425 @default.
- W4317496738 creator A5058120371 @default.
- W4317496738 date "2023-06-15" @default.
- W4317496738 modified "2023-10-06" @default.
- W4317496738 title "Accuracy Degrading: Toward Participation-Fair Federated Learning" @default.
- W4317496738 cites W2096870293 @default.
- W4317496738 cites W2473418344 @default.
- W4317496738 cites W2535690855 @default.
- W4317496738 cites W2576683119 @default.
- W4317496738 cites W2911978475 @default.
- W4317496738 cites W2978422189 @default.
- W4317496738 cites W2979506454 @default.
- W4317496738 cites W3001299093 @default.
- W4317496738 cites W3012990321 @default.
- W4317496738 cites W3016632787 @default.
- W4317496738 cites W3023244064 @default.
- W4317496738 cites W3027472889 @default.
- W4317496738 cites W3027749727 @default.
- W4317496738 cites W3103802018 @default.
- W4317496738 cites W3105122387 @default.
- W4317496738 cites W3109723249 @default.
- W4317496738 cites W3110928794 @default.
- W4317496738 cites W3156681210 @default.
- W4317496738 cites W3161225848 @default.
- W4317496738 cites W3213321731 @default.
- W4317496738 cites W4200419653 @default.
- W4317496738 cites W4225310475 @default.
- W4317496738 cites W4285722492 @default.
- W4317496738 cites W4294106961 @default.
- W4317496738 doi "https://doi.org/10.1109/jiot.2023.3238038" @default.
- W4317496738 hasPublicationYear "2023" @default.
- W4317496738 type Work @default.
- W4317496738 citedByCount "0" @default.
- W4317496738 crossrefType "journal-article" @default.
- W4317496738 hasAuthorship W4317496738A5001657111 @default.
- W4317496738 hasAuthorship W4317496738A5034637087 @default.
- W4317496738 hasAuthorship W4317496738A5052779809 @default.
- W4317496738 hasAuthorship W4317496738A5052928425 @default.
- W4317496738 hasAuthorship W4317496738A5058120371 @default.
- W4317496738 hasConcept C111919701 @default.
- W4317496738 hasConcept C119857082 @default.
- W4317496738 hasConcept C123201435 @default.
- W4317496738 hasConcept C123657996 @default.
- W4317496738 hasConcept C124101348 @default.
- W4317496738 hasConcept C142362112 @default.
- W4317496738 hasConcept C153349607 @default.
- W4317496738 hasConcept C154945302 @default.
- W4317496738 hasConcept C23130292 @default.
- W4317496738 hasConcept C2775924081 @default.
- W4317496738 hasConcept C2992525071 @default.
- W4317496738 hasConcept C38652104 @default.
- W4317496738 hasConcept C41008148 @default.
- W4317496738 hasConcept C527821871 @default.
- W4317496738 hasConcept C98045186 @default.
- W4317496738 hasConceptScore W4317496738C111919701 @default.
- W4317496738 hasConceptScore W4317496738C119857082 @default.
- W4317496738 hasConceptScore W4317496738C123201435 @default.
- W4317496738 hasConceptScore W4317496738C123657996 @default.
- W4317496738 hasConceptScore W4317496738C124101348 @default.
- W4317496738 hasConceptScore W4317496738C142362112 @default.
- W4317496738 hasConceptScore W4317496738C153349607 @default.
- W4317496738 hasConceptScore W4317496738C154945302 @default.
- W4317496738 hasConceptScore W4317496738C23130292 @default.
- W4317496738 hasConceptScore W4317496738C2775924081 @default.
- W4317496738 hasConceptScore W4317496738C2992525071 @default.
- W4317496738 hasConceptScore W4317496738C38652104 @default.
- W4317496738 hasConceptScore W4317496738C41008148 @default.
- W4317496738 hasConceptScore W4317496738C527821871 @default.
- W4317496738 hasConceptScore W4317496738C98045186 @default.
- W4317496738 hasFunder F4320321001 @default.
- W4317496738 hasFunder F4320321878 @default.
- W4317496738 hasIssue "12" @default.
- W4317496738 hasLocation W43174967381 @default.
- W4317496738 hasOpenAccess W4317496738 @default.
- W4317496738 hasPrimaryLocation W43174967381 @default.
- W4317496738 hasRelatedWork W2385157860 @default.
- W4317496738 hasRelatedWork W2969945192 @default.
- W4317496738 hasRelatedWork W3008343982 @default.
- W4317496738 hasRelatedWork W4225823290 @default.
- W4317496738 hasRelatedWork W4287865753 @default.
- W4317496738 hasRelatedWork W4360993981 @default.
- W4317496738 hasRelatedWork W4366307888 @default.
- W4317496738 hasRelatedWork W4383047473 @default.
- W4317496738 hasRelatedWork W4383469366 @default.
- W4317496738 hasRelatedWork W4386597430 @default.
- W4317496738 hasVolume "10" @default.
- W4317496738 isParatext "false" @default.
- W4317496738 isRetracted "false" @default.
- W4317496738 workType "article" @default.