FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312357259> ?p ?o ?g. }

• W4312357259 endingPage "131" @default.
• W4312357259 startingPage "119" @default.
• W4312357259 abstract "Federated learning (FL) aims to raise a multi-client collaboration approach in the case of local data isolation. In particular, the clients with non-IID data frequently participate in or leave the federated learning training process asynchronously, resulting in dynamic federated learning (DFL) scenario, which attracts more and more attention. Indeed, an effective DFL solution has to address the following two challenges: 1) Statistical Dynamics. The distributions of local data from clients are always non-IID and the global data distribution is dynamic due to the participation or departure of clients. 2) Expiration Dynamics. After clients leave the federated training process, their historical updated models have a certain validity to reuse in subsequent rounds but it is hard to quantify this validity. In this paper, we first consider clustering the clients with similar data distribution to make them much closer to IID and concentrating on the training the models in each cluster. Then we analyze the changing trend of model validity named model quality and define one suitable function to describe expiration dynamics. As a solution, we propose Dynamic Clustering Federated Learning (DCFL) framework to improve federated learning on non-IID data in DFL. Specifically, DCFL follows the client-server architecture as the standard FL. On the client side, the local devices calculate the related information of the local data distribution for client clustering. On the server side, we design two strategies for the challenges above. We propose dynamic clustering aggregation strategy (including a dynamic clustering algorithm and a two-stage aggregation) by dynamically clustering clients and then aggregating the local models to overcome Statistical Dynamics. Besides, we propose expiration memory strategy by reusing the historical models and then adjusting to model quality of historical models as the basis for model aggregation to overcome Expiration Dynamics. Finally, we conduct extensive experiments on public datasets, which demonstrate the effectiveness of the DCFL framework." @default.
• W4312357259 created "2023-01-04" @default.
• W4312357259 creator A5002666071 @default.
• W4312357259 creator A5014264612 @default.
• W4312357259 creator A5015037796 @default.
• W4312357259 creator A5048237545 @default.
• W4312357259 creator A5085028455 @default.
• W4312357259 creator A5085496384 @default.
• W4312357259 date "2022-01-01" @default.
• W4312357259 modified "2023-09-25" @default.
• W4312357259 title "Dynamic Clustering Federated Learning for Non-IID Data" @default.
• W4312357259 cites W1977556410 @default.
• W4312357259 cites W2032873009 @default.
• W4312357259 cites W2035890032 @default.
• W4312357259 cites W2051224630 @default.
• W4312357259 cites W2067072670 @default.
• W4312357259 cites W2108323654 @default.
• W4312357259 cites W2120467292 @default.
• W4312357259 cites W2744790096 @default.
• W4312357259 cites W2912213068 @default.
• W4312357259 cites W2955931418 @default.
• W4312357259 cites W3005429940 @default.
• W4312357259 cites W3080934299 @default.
• W4312357259 cites W3081178085 @default.
• W4312357259 cites W3100760018 @default.
• W4312357259 cites W3102496129 @default.
• W4312357259 cites W3109723249 @default.
• W4312357259 cites W3116287258 @default.
• W4312357259 cites W3127520698 @default.
• W4312357259 cites W3156467244 @default.
• W4312357259 cites W3156841666 @default.
• W4312357259 cites W3191604281 @default.
• W4312357259 cites W4200419653 @default.
• W4312357259 cites W4213044365 @default.
• W4312357259 doi "https://doi.org/10.1007/978-3-031-20503-3_10" @default.
• W4312357259 hasPublicationYear "2022" @default.
• W4312357259 type Work @default.
• W4312357259 citedByCount "0" @default.
• W4312357259 crossrefType "book-chapter" @default.
• W4312357259 hasAuthorship W4312357259A5002666071 @default.
• W4312357259 hasAuthorship W4312357259A5014264612 @default.
• W4312357259 hasAuthorship W4312357259A5015037796 @default.
• W4312357259 hasAuthorship W4312357259A5048237545 @default.
• W4312357259 hasAuthorship W4312357259A5085028455 @default.
• W4312357259 hasAuthorship W4312357259A5085496384 @default.
• W4312357259 hasConcept C111919701 @default.
• W4312357259 hasConcept C119857082 @default.
• W4312357259 hasConcept C124101348 @default.
• W4312357259 hasConcept C154945302 @default.
• W4312357259 hasConcept C197298091 @default.
• W4312357259 hasConcept C2992525071 @default.
• W4312357259 hasConcept C41008148 @default.
• W4312357259 hasConcept C73555534 @default.
• W4312357259 hasConcept C77088390 @default.
• W4312357259 hasConcept C98045186 @default.
• W4312357259 hasConceptScore W4312357259C111919701 @default.
• W4312357259 hasConceptScore W4312357259C119857082 @default.
• W4312357259 hasConceptScore W4312357259C124101348 @default.
• W4312357259 hasConceptScore W4312357259C154945302 @default.
• W4312357259 hasConceptScore W4312357259C197298091 @default.
• W4312357259 hasConceptScore W4312357259C2992525071 @default.
• W4312357259 hasConceptScore W4312357259C41008148 @default.
• W4312357259 hasConceptScore W4312357259C73555534 @default.
• W4312357259 hasConceptScore W4312357259C77088390 @default.
• W4312357259 hasConceptScore W4312357259C98045186 @default.
• W4312357259 hasLocation W43123572591 @default.
• W4312357259 hasOpenAccess W4312357259 @default.
• W4312357259 hasPrimaryLocation W43123572591 @default.
• W4312357259 hasRelatedWork W1999627569 @default.
• W4312357259 hasRelatedWork W2280471592 @default.
• W4312357259 hasRelatedWork W2380998760 @default.
• W4312357259 hasRelatedWork W2518702994 @default.
• W4312357259 hasRelatedWork W2961085424 @default.
• W4312357259 hasRelatedWork W4286629047 @default.
• W4312357259 hasRelatedWork W4306674287 @default.
• W4312357259 hasRelatedWork W4312357259 @default.
• W4312357259 hasRelatedWork W763609066 @default.
• W4312357259 hasRelatedWork W4224009465 @default.
• W4312357259 isParatext "false" @default.
• W4312357259 isRetracted "false" @default.
• W4312357259 workType "book-chapter" @default.