Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308449507> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4308449507 endingPage "2099" @default.
- W4308449507 startingPage "2081" @default.
- W4308449507 abstract "Abstract Federated learning (FL) is a new distributed learning framework that is different from traditional distributed machine learning: (1) differences in communication, computing, and storage performance among devices (device heterogeneity), (2) differences in data distribution and data volume (data heterogeneity), and (3) high communication consumption. Under heterogeneous conditions, the data distribution of clients varies greatly, which leads to the problem that the convergence speed of the training model decreases and the training model cannot converge to the global optimal solution. In this work, an FL algorithm based on stratified sampling and regularization (FedSSAR) is proposed. In FedSSAR, a density-based clustering method is used to divide the overall client into different clusters, then, some available clients are proportionally extracted from different clusters to participate in training which realizes unbiased sampling for the overall client and reduces the aggregation weight variance of the client. At the same time, when calculating the model local loss function, we limit the update direction of the model by a regular term, so that heterogeneous clients are optimized in the globally optimal direction. We prove the convergence of FedSSAR theoretically and experimentally, and demonstrate the superiority of FedSSAR by comparing it with other FL algorithms on public datasets." @default.
- W4308449507 created "2022-11-12" @default.
- W4308449507 creator A5044323526 @default.
- W4308449507 creator A5055284175 @default.
- W4308449507 creator A5058240238 @default.
- W4308449507 creator A5070812231 @default.
- W4308449507 creator A5073231342 @default.
- W4308449507 date "2022-11-07" @default.
- W4308449507 modified "2023-09-25" @default.
- W4308449507 title "Federated learning based on stratified sampling and regularization" @default.
- W4308449507 cites W2767079719 @default.
- W4308449507 cites W2912213068 @default.
- W4308449507 cites W2998174899 @default.
- W4308449507 cites W3080934299 @default.
- W4308449507 cites W3103802018 @default.
- W4308449507 cites W3112044954 @default.
- W4308449507 cites W4206320562 @default.
- W4308449507 cites W4292363360 @default.
- W4308449507 doi "https://doi.org/10.1007/s40747-022-00895-3" @default.
- W4308449507 hasPublicationYear "2022" @default.
- W4308449507 type Work @default.
- W4308449507 citedByCount "1" @default.
- W4308449507 countsByYear W43084495072023 @default.
- W4308449507 crossrefType "journal-article" @default.
- W4308449507 hasAuthorship W4308449507A5044323526 @default.
- W4308449507 hasAuthorship W4308449507A5055284175 @default.
- W4308449507 hasAuthorship W4308449507A5058240238 @default.
- W4308449507 hasAuthorship W4308449507A5070812231 @default.
- W4308449507 hasAuthorship W4308449507A5073231342 @default.
- W4308449507 hasBestOaLocation W43084495071 @default.
- W4308449507 hasConcept C105795698 @default.
- W4308449507 hasConcept C106131492 @default.
- W4308449507 hasConcept C119857082 @default.
- W4308449507 hasConcept C121955636 @default.
- W4308449507 hasConcept C124101348 @default.
- W4308449507 hasConcept C140779682 @default.
- W4308449507 hasConcept C144133560 @default.
- W4308449507 hasConcept C154945302 @default.
- W4308449507 hasConcept C162324750 @default.
- W4308449507 hasConcept C19499675 @default.
- W4308449507 hasConcept C196083921 @default.
- W4308449507 hasConcept C2776135515 @default.
- W4308449507 hasConcept C2777303404 @default.
- W4308449507 hasConcept C31972630 @default.
- W4308449507 hasConcept C33923547 @default.
- W4308449507 hasConcept C41008148 @default.
- W4308449507 hasConcept C50522688 @default.
- W4308449507 hasConcept C52740198 @default.
- W4308449507 hasConcept C73555534 @default.
- W4308449507 hasConceptScore W4308449507C105795698 @default.
- W4308449507 hasConceptScore W4308449507C106131492 @default.
- W4308449507 hasConceptScore W4308449507C119857082 @default.
- W4308449507 hasConceptScore W4308449507C121955636 @default.
- W4308449507 hasConceptScore W4308449507C124101348 @default.
- W4308449507 hasConceptScore W4308449507C140779682 @default.
- W4308449507 hasConceptScore W4308449507C144133560 @default.
- W4308449507 hasConceptScore W4308449507C154945302 @default.
- W4308449507 hasConceptScore W4308449507C162324750 @default.
- W4308449507 hasConceptScore W4308449507C19499675 @default.
- W4308449507 hasConceptScore W4308449507C196083921 @default.
- W4308449507 hasConceptScore W4308449507C2776135515 @default.
- W4308449507 hasConceptScore W4308449507C2777303404 @default.
- W4308449507 hasConceptScore W4308449507C31972630 @default.
- W4308449507 hasConceptScore W4308449507C33923547 @default.
- W4308449507 hasConceptScore W4308449507C41008148 @default.
- W4308449507 hasConceptScore W4308449507C50522688 @default.
- W4308449507 hasConceptScore W4308449507C52740198 @default.
- W4308449507 hasConceptScore W4308449507C73555534 @default.
- W4308449507 hasIssue "2" @default.
- W4308449507 hasLocation W43084495071 @default.
- W4308449507 hasOpenAccess W4308449507 @default.
- W4308449507 hasPrimaryLocation W43084495071 @default.
- W4308449507 hasRelatedWork W1965320053 @default.
- W4308449507 hasRelatedWork W2006722592 @default.
- W4308449507 hasRelatedWork W2125528412 @default.
- W4308449507 hasRelatedWork W2568411832 @default.
- W4308449507 hasRelatedWork W3202114911 @default.
- W4308449507 hasRelatedWork W4221151455 @default.
- W4308449507 hasRelatedWork W4248659657 @default.
- W4308449507 hasRelatedWork W4285069894 @default.
- W4308449507 hasRelatedWork W4294175445 @default.
- W4308449507 hasRelatedWork W4307073206 @default.
- W4308449507 hasVolume "9" @default.
- W4308449507 isParatext "false" @default.
- W4308449507 isRetracted "false" @default.
- W4308449507 workType "article" @default.