Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362714756> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4362714756 endingPage "12" @default.
- W4362714756 startingPage "1" @default.
- W4362714756 abstract "Federated Learning (FL) has shown great potential as a privacy-preserving solution to learning from decentralized data that are only accessible to end devices (i.e., clients). The data locality constraint offers strong privacy protection but also makes FL sensitive to the condition of local data. Apart from statistical heterogeneity, a large proportion of the clients, in many scenarios, are probably in possession of low-quality data that are biased, noisy or even irrelevant. As a result, they could significantly slow down the convergence of the global model we aim to build and also compromise its quality. In light of this, we first present a new view of local data by looking into the representation space and observing that they converge in distribution to Normal distributions before activation. We provide theoretical analysis to support our finding. Further, we propose <sc xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>FedProf</small> , a novel algorithm for optimizing FL over non-IID data of mixed quality. The key of our approach is a distributional representation profiling and matching scheme that uses the global model to dynamically profile data representations and allows for low-cost, lightweight representation matching. Using the scheme we sample clients adaptively in FL to mitigate the impact of low-quality data on the training process. We evaluated our solution with extensive experiments on different tasks and data conditions under various FL settings. The results demonstrate that the selective behavior of our algorithm leads to a significant reduction in the number of communication rounds and the amount of time (up to 2.4× speedup) for the global model to converge and also provides accuracy gain." @default.
- W4362714756 created "2023-04-09" @default.
- W4362714756 creator A5007440245 @default.
- W4362714756 creator A5010184733 @default.
- W4362714756 creator A5030234311 @default.
- W4362714756 creator A5064596191 @default.
- W4362714756 date "2023-01-01" @default.
- W4362714756 modified "2023-09-27" @default.
- W4362714756 title "FedProf: Selective Federated Learning based on Distributional Representation Profiling" @default.
- W4362714756 doi "https://doi.org/10.1109/tpds.2023.3265588" @default.
- W4362714756 hasPublicationYear "2023" @default.
- W4362714756 type Work @default.
- W4362714756 citedByCount "1" @default.
- W4362714756 countsByYear W43627147562023 @default.
- W4362714756 crossrefType "journal-article" @default.
- W4362714756 hasAuthorship W4362714756A5007440245 @default.
- W4362714756 hasAuthorship W4362714756A5010184733 @default.
- W4362714756 hasAuthorship W4362714756A5030234311 @default.
- W4362714756 hasAuthorship W4362714756A5064596191 @default.
- W4362714756 hasConcept C105795698 @default.
- W4362714756 hasConcept C108827166 @default.
- W4362714756 hasConcept C111919701 @default.
- W4362714756 hasConcept C116409475 @default.
- W4362714756 hasConcept C119857082 @default.
- W4362714756 hasConcept C123201435 @default.
- W4362714756 hasConcept C124101348 @default.
- W4362714756 hasConcept C138885662 @default.
- W4362714756 hasConcept C154945302 @default.
- W4362714756 hasConcept C165064840 @default.
- W4362714756 hasConcept C17744445 @default.
- W4362714756 hasConcept C187191949 @default.
- W4362714756 hasConcept C199539241 @default.
- W4362714756 hasConcept C2776359362 @default.
- W4362714756 hasConcept C2779808786 @default.
- W4362714756 hasConcept C33923547 @default.
- W4362714756 hasConcept C41008148 @default.
- W4362714756 hasConcept C41895202 @default.
- W4362714756 hasConcept C80444323 @default.
- W4362714756 hasConcept C94625758 @default.
- W4362714756 hasConceptScore W4362714756C105795698 @default.
- W4362714756 hasConceptScore W4362714756C108827166 @default.
- W4362714756 hasConceptScore W4362714756C111919701 @default.
- W4362714756 hasConceptScore W4362714756C116409475 @default.
- W4362714756 hasConceptScore W4362714756C119857082 @default.
- W4362714756 hasConceptScore W4362714756C123201435 @default.
- W4362714756 hasConceptScore W4362714756C124101348 @default.
- W4362714756 hasConceptScore W4362714756C138885662 @default.
- W4362714756 hasConceptScore W4362714756C154945302 @default.
- W4362714756 hasConceptScore W4362714756C165064840 @default.
- W4362714756 hasConceptScore W4362714756C17744445 @default.
- W4362714756 hasConceptScore W4362714756C187191949 @default.
- W4362714756 hasConceptScore W4362714756C199539241 @default.
- W4362714756 hasConceptScore W4362714756C2776359362 @default.
- W4362714756 hasConceptScore W4362714756C2779808786 @default.
- W4362714756 hasConceptScore W4362714756C33923547 @default.
- W4362714756 hasConceptScore W4362714756C41008148 @default.
- W4362714756 hasConceptScore W4362714756C41895202 @default.
- W4362714756 hasConceptScore W4362714756C80444323 @default.
- W4362714756 hasConceptScore W4362714756C94625758 @default.
- W4362714756 hasLocation W43627147561 @default.
- W4362714756 hasOpenAccess W4362714756 @default.
- W4362714756 hasPrimaryLocation W43627147561 @default.
- W4362714756 hasRelatedWork W1498242466 @default.
- W4362714756 hasRelatedWork W1515687668 @default.
- W4362714756 hasRelatedWork W180873246 @default.
- W4362714756 hasRelatedWork W2055387065 @default.
- W4362714756 hasRelatedWork W2143043355 @default.
- W4362714756 hasRelatedWork W2253991048 @default.
- W4362714756 hasRelatedWork W2363235386 @default.
- W4362714756 hasRelatedWork W3001095776 @default.
- W4362714756 hasRelatedWork W3001496086 @default.
- W4362714756 hasRelatedWork W3217401397 @default.
- W4362714756 isParatext "false" @default.
- W4362714756 isRetracted "false" @default.
- W4362714756 workType "article" @default.