Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281489575> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4281489575 endingPage "120255" @default.
- W4281489575 startingPage "120245" @default.
- W4281489575 abstract "Personalized Federated Learning (FL) is an emerging research field in FL that learns an easily adaptable global model in the presence of data heterogeneity among clients. However, one of the main challenges for personalized FL is the heavy reliance on clients’ computing resources to calculate higher-order gradients since client data is segregated from the server to ensure privacy. To resolve this, we focus on a problem setting where the server may possess data independent of clients’ data – a prevalent problem setting in various applications, yet relatively unexplored in the existing literature. Specifically, we propose FedSIM, a new method for personalized FL that actively utilizes such <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>server data</i> to improve meta-gradient calculation in the server for increased personalization performance. Experimentally, we demonstrate through various benchmarks and ablations that FedSIM is superior to existing methods in terms of accuracy, more computationally efficient by calculating the full meta-gradients in the server, and converges up to 34.2% faster." @default.
- W4281489575 created "2022-05-26" @default.
- W4281489575 creator A5000439697 @default.
- W4281489575 creator A5006205893 @default.
- W4281489575 creator A5065781070 @default.
- W4281489575 date "2022-01-01" @default.
- W4281489575 modified "2023-10-14" @default.
- W4281489575 title "Personalized Federated Learning With Server-Side Information" @default.
- W4281489575 cites W2133665775 @default.
- W4281489575 cites W2734358244 @default.
- W4281489575 cites W2908659529 @default.
- W4281489575 cites W2963318081 @default.
- W4281489575 cites W3014867431 @default.
- W4281489575 cites W3103802018 @default.
- W4281489575 cites W4221158339 @default.
- W4281489575 doi "https://doi.org/10.1109/access.2022.3221401" @default.
- W4281489575 hasPublicationYear "2022" @default.
- W4281489575 type Work @default.
- W4281489575 citedByCount "2" @default.
- W4281489575 countsByYear W42814895752023 @default.
- W4281489575 crossrefType "journal-article" @default.
- W4281489575 hasAuthorship W4281489575A5000439697 @default.
- W4281489575 hasAuthorship W4281489575A5006205893 @default.
- W4281489575 hasAuthorship W4281489575A5065781070 @default.
- W4281489575 hasBestOaLocation W42814895751 @default.
- W4281489575 hasConcept C120314980 @default.
- W4281489575 hasConcept C120665830 @default.
- W4281489575 hasConcept C121332964 @default.
- W4281489575 hasConcept C136764020 @default.
- W4281489575 hasConcept C14414571 @default.
- W4281489575 hasConcept C183003079 @default.
- W4281489575 hasConcept C192209626 @default.
- W4281489575 hasConcept C202444582 @default.
- W4281489575 hasConcept C2992525071 @default.
- W4281489575 hasConcept C33923547 @default.
- W4281489575 hasConcept C41008148 @default.
- W4281489575 hasConcept C77088390 @default.
- W4281489575 hasConcept C93996380 @default.
- W4281489575 hasConcept C9652623 @default.
- W4281489575 hasConceptScore W4281489575C120314980 @default.
- W4281489575 hasConceptScore W4281489575C120665830 @default.
- W4281489575 hasConceptScore W4281489575C121332964 @default.
- W4281489575 hasConceptScore W4281489575C136764020 @default.
- W4281489575 hasConceptScore W4281489575C14414571 @default.
- W4281489575 hasConceptScore W4281489575C183003079 @default.
- W4281489575 hasConceptScore W4281489575C192209626 @default.
- W4281489575 hasConceptScore W4281489575C202444582 @default.
- W4281489575 hasConceptScore W4281489575C2992525071 @default.
- W4281489575 hasConceptScore W4281489575C33923547 @default.
- W4281489575 hasConceptScore W4281489575C41008148 @default.
- W4281489575 hasConceptScore W4281489575C77088390 @default.
- W4281489575 hasConceptScore W4281489575C93996380 @default.
- W4281489575 hasConceptScore W4281489575C9652623 @default.
- W4281489575 hasFunder F4320321292 @default.
- W4281489575 hasLocation W42814895751 @default.
- W4281489575 hasLocation W42814895752 @default.
- W4281489575 hasLocation W42814895753 @default.
- W4281489575 hasOpenAccess W4281489575 @default.
- W4281489575 hasPrimaryLocation W42814895751 @default.
- W4281489575 hasRelatedWork W1583717361 @default.
- W4281489575 hasRelatedWork W2108595774 @default.
- W4281489575 hasRelatedWork W2323581027 @default.
- W4281489575 hasRelatedWork W2383377700 @default.
- W4281489575 hasRelatedWork W2748952813 @default.
- W4281489575 hasRelatedWork W3128909129 @default.
- W4281489575 hasRelatedWork W4226111152 @default.
- W4281489575 hasRelatedWork W4281489575 @default.
- W4281489575 hasRelatedWork W4320812421 @default.
- W4281489575 hasRelatedWork W87991986 @default.
- W4281489575 hasVolume "10" @default.
- W4281489575 isParatext "false" @default.
- W4281489575 isRetracted "false" @default.
- W4281489575 workType "article" @default.