FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308648313> ?p ?o ?g. }

• W4308648313 endingPage "19" @default.
• W4308648313 startingPage "1" @default.
• W4308648313 abstract "Federated learning (FL), a distributed machine-learning framework, is poised to effectively protect data privacy and security, and it also has been widely applied in variety of fields in recent years. However, the system heterogeneity and statistical heterogeneity of FL pose serious obstacles to the global model's quality. This study investigates server and client resource allocation in the context of FL system resource efficiency and offers the FedAwo optimization algorithm. This approach combines adaptive learning with federated learning, and makes full use of the computing resources of the server to calculate the optimal weight value corresponding to each client. This approach aggregated the global model according to the optimal weight value, which significantly minimizes the detrimental effects of statistical and system heterogeneity. In the process of traditional FL, we found that a large number of client trainings converge earlier than the specified epoch. However, according to the provisions of traditional FL, the client still needs to be trained for the specified epoch, which leads to the meaningless of a large number of calculations in the client. To further lower the training cost, the augmentation FedAwo ∗ algorithm is proposed. The FedAwo ∗ algorithm takes into account the heterogeneity of clients and sets the criteria for local convergence. When the local model of the client reaches the criteria, it will be returned to the server immediately. In this way, the epoch of the client can dynamically be modified adaptively. A large number of experiments based on MNIST and Fashion-MNIST public datasets reveal that the global model converges faster and has higher accuracy in FedAwo and FedAwo ∗ algorithms than FedAvg, FedProx, and FedAdp baseline algorithms." @default.
• W4308648313 created "2022-11-13" @default.
• W4308648313 creator A5027475930 @default.
• W4308648313 creator A5041259291 @default.
• W4308648313 creator A5057994434 @default.
• W4308648313 creator A5062618254 @default.
• W4308648313 creator A5072801590 @default.
• W4308648313 date "2022-11-09" @default.
• W4308648313 modified "2023-10-14" @default.
• W4308648313 title "Federated Learning Optimization Algorithm for Automatic Weight Optimal" @default.
• W4308648313 cites W1547816371 @default.
• W4308648313 cites W2795102035 @default.
• W4308648313 cites W2900182564 @default.
• W4308648313 cites W2920095265 @default.
• W4308648313 cites W2963318081 @default.
• W4308648313 cites W2970885630 @default.
• W4308648313 cites W2977072935 @default.
• W4308648313 cites W3016839154 @default.
• W4308648313 cites W3113075536 @default.
• W4308648313 cites W3155160971 @default.
• W4308648313 cites W3162353295 @default.
• W4308648313 cites W3170790803 @default.
• W4308648313 cites W3194243671 @default.
• W4308648313 cites W3200400919 @default.
• W4308648313 cites W4224139907 @default.
• W4308648313 cites W4229082374 @default.
• W4308648313 doi "https://doi.org/10.1155/2022/8342638" @default.
• W4308648313 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36407688" @default.
• W4308648313 hasPublicationYear "2022" @default.
• W4308648313 type Work @default.
• W4308648313 citedByCount "0" @default.
• W4308648313 crossrefType "journal-article" @default.
• W4308648313 hasAuthorship W4308648313A5027475930 @default.
• W4308648313 hasAuthorship W4308648313A5041259291 @default.
• W4308648313 hasAuthorship W4308648313A5057994434 @default.
• W4308648313 hasAuthorship W4308648313A5062618254 @default.
• W4308648313 hasAuthorship W4308648313A5072801590 @default.
• W4308648313 hasBestOaLocation W43086483131 @default.
• W4308648313 hasConcept C111472728 @default.
• W4308648313 hasConcept C111919701 @default.
• W4308648313 hasConcept C11413529 @default.
• W4308648313 hasConcept C119857082 @default.
• W4308648313 hasConcept C138885662 @default.
• W4308648313 hasConcept C150846664 @default.
• W4308648313 hasConcept C151730666 @default.
• W4308648313 hasConcept C154945302 @default.
• W4308648313 hasConcept C162324750 @default.
• W4308648313 hasConcept C164752517 @default.
• W4308648313 hasConcept C190502265 @default.
• W4308648313 hasConcept C2777303404 @default.
• W4308648313 hasConcept C2779343474 @default.
• W4308648313 hasConcept C2779530757 @default.
• W4308648313 hasConcept C2780317896 @default.
• W4308648313 hasConcept C31972630 @default.
• W4308648313 hasConcept C41008148 @default.
• W4308648313 hasConcept C50522688 @default.
• W4308648313 hasConcept C50644808 @default.
• W4308648313 hasConcept C86803240 @default.
• W4308648313 hasConcept C98045186 @default.
• W4308648313 hasConceptScore W4308648313C111472728 @default.
• W4308648313 hasConceptScore W4308648313C111919701 @default.
• W4308648313 hasConceptScore W4308648313C11413529 @default.
• W4308648313 hasConceptScore W4308648313C119857082 @default.
• W4308648313 hasConceptScore W4308648313C138885662 @default.
• W4308648313 hasConceptScore W4308648313C150846664 @default.
• W4308648313 hasConceptScore W4308648313C151730666 @default.
• W4308648313 hasConceptScore W4308648313C154945302 @default.
• W4308648313 hasConceptScore W4308648313C162324750 @default.
• W4308648313 hasConceptScore W4308648313C164752517 @default.
• W4308648313 hasConceptScore W4308648313C190502265 @default.
• W4308648313 hasConceptScore W4308648313C2777303404 @default.
• W4308648313 hasConceptScore W4308648313C2779343474 @default.
• W4308648313 hasConceptScore W4308648313C2779530757 @default.
• W4308648313 hasConceptScore W4308648313C2780317896 @default.
• W4308648313 hasConceptScore W4308648313C31972630 @default.
• W4308648313 hasConceptScore W4308648313C41008148 @default.
• W4308648313 hasConceptScore W4308648313C50522688 @default.
• W4308648313 hasConceptScore W4308648313C50644808 @default.
• W4308648313 hasConceptScore W4308648313C86803240 @default.
• W4308648313 hasConceptScore W4308648313C98045186 @default.
• W4308648313 hasFunder F4320327051 @default.
• W4308648313 hasLocation W43086483131 @default.
• W4308648313 hasLocation W43086483132 @default.
• W4308648313 hasLocation W43086483133 @default.
• W4308648313 hasLocation W43086483134 @default.
• W4308648313 hasOpenAccess W4308648313 @default.
• W4308648313 hasPrimaryLocation W43086483131 @default.
• W4308648313 hasRelatedWork W2276478028 @default.
• W4308648313 hasRelatedWork W2597787948 @default.
• W4308648313 hasRelatedWork W2947175736 @default.
• W4308648313 hasRelatedWork W2961085424 @default.
• W4308648313 hasRelatedWork W3012135218 @default.
• W4308648313 hasRelatedWork W4286629047 @default.
• W4308648313 hasRelatedWork W4306321456 @default.
• W4308648313 hasRelatedWork W4306674287 @default.
• W4308648313 hasRelatedWork W4308648313 @default.
• W4308648313 hasRelatedWork W4224009465 @default.
• W4308648313 hasVolume "2022" @default.

• next