FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4296350897> ?p ?o ?g. }

• W4296350897 endingPage "7061" @default.
• W4296350897 startingPage "7061" @default.
• W4296350897 abstract "Federated learning (FL) is a promising collaborative learning approach in edge computing, reducing communication costs and addressing the data privacy concerns of traditional cloud-based training. Owing to this, diverse studies have been conducted to distribute FL into industry. However, there still remain the practical issues of FL to be solved (e.g., handling non-IID data and stragglers) for an actual implementation of FL. To address these issues, in this paper, we propose a cluster-driven adaptive training approach (CATA-Fed) to enhance the performance of FL training in a practical environment. CATA-Fed employs adaptive training during the local model updates to enhance the efficiency of training, reducing the waste of time and resources due to the presence of the stragglers and also provides a straggler mitigating scheme, which can reduce the workload of straggling clients. In addition to this, CATA-Fed clusters the clients considering the data size and selects the training participants within a cluster to reduce the magnitude differences of local gradients collected in the global model update under a statistical heterogeneous condition (e.g., non-IID data). During this client selection process, a proportional fair scheduling is employed for securing the data diversity as well as balancing the load of clients. We conduct extensive experiments using three benchmark datasets (MNIST, Fashion-MNIST, and CIFAR-10), and the results show that CATA-Fed outperforms the previous FL schemes (FedAVG, FedProx, and TiFL) with regard to the training speed and test accuracy under the diverse FL conditions." @default.
• W4296350897 created "2022-09-20" @default.
• W4296350897 creator A5022989333 @default.
• W4296350897 creator A5036555913 @default.
• W4296350897 date "2022-09-18" @default.
• W4296350897 modified "2023-10-01" @default.
• W4296350897 title "A Cluster-Driven Adaptive Training Approach for Federated Learning" @default.
• W4296350897 cites W2509544990 @default.
• W4296350897 cites W2900182564 @default.
• W4296350897 cites W2954996726 @default.
• W4296350897 cites W2963318081 @default.
• W4296350897 cites W2989289980 @default.
• W4296350897 cites W3037871107 @default.
• W4296350897 cites W3047304572 @default.
• W4296350897 cites W3117983928 @default.
• W4296350897 cites W3159080474 @default.
• W4296350897 cites W3194922990 @default.
• W4296350897 cites W3196371845 @default.
• W4296350897 cites W3213802103 @default.
• W4296350897 cites W4200571368 @default.
• W4296350897 cites W4211249696 @default.
• W4296350897 cites W4224100171 @default.
• W4296350897 cites W4285170564 @default.
• W4296350897 cites W4294106961 @default.
• W4296350897 doi "https://doi.org/10.3390/s22187061" @default.
• W4296350897 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36146408" @default.
• W4296350897 hasPublicationYear "2022" @default.
• W4296350897 type Work @default.
• W4296350897 citedByCount "2" @default.
• W4296350897 countsByYear W42963508972022 @default.
• W4296350897 countsByYear W42963508972023 @default.
• W4296350897 crossrefType "journal-article" @default.
• W4296350897 hasAuthorship W4296350897A5022989333 @default.
• W4296350897 hasAuthorship W4296350897A5036555913 @default.
• W4296350897 hasBestOaLocation W42963508971 @default.
• W4296350897 hasConcept C111919701 @default.
• W4296350897 hasConcept C119857082 @default.
• W4296350897 hasConcept C120314980 @default.
• W4296350897 hasConcept C120665830 @default.
• W4296350897 hasConcept C121332964 @default.
• W4296350897 hasConcept C124101348 @default.
• W4296350897 hasConcept C127413603 @default.
• W4296350897 hasConcept C13280743 @default.
• W4296350897 hasConcept C139807058 @default.
• W4296350897 hasConcept C153294291 @default.
• W4296350897 hasConcept C154945302 @default.
• W4296350897 hasConcept C162307627 @default.
• W4296350897 hasConcept C164866538 @default.
• W4296350897 hasConcept C185798385 @default.
• W4296350897 hasConcept C190502265 @default.
• W4296350897 hasConcept C205649164 @default.
• W4296350897 hasConcept C206729178 @default.
• W4296350897 hasConcept C21547014 @default.
• W4296350897 hasConcept C2777211547 @default.
• W4296350897 hasConcept C2778476105 @default.
• W4296350897 hasConcept C2992525071 @default.
• W4296350897 hasConcept C31258907 @default.
• W4296350897 hasConcept C41008148 @default.
• W4296350897 hasConcept C50644808 @default.
• W4296350897 hasConcept C79974875 @default.
• W4296350897 hasConcept C98045186 @default.
• W4296350897 hasConceptScore W4296350897C111919701 @default.
• W4296350897 hasConceptScore W4296350897C119857082 @default.
• W4296350897 hasConceptScore W4296350897C120314980 @default.
• W4296350897 hasConceptScore W4296350897C120665830 @default.
• W4296350897 hasConceptScore W4296350897C121332964 @default.
• W4296350897 hasConceptScore W4296350897C124101348 @default.
• W4296350897 hasConceptScore W4296350897C127413603 @default.
• W4296350897 hasConceptScore W4296350897C13280743 @default.
• W4296350897 hasConceptScore W4296350897C139807058 @default.
• W4296350897 hasConceptScore W4296350897C153294291 @default.
• W4296350897 hasConceptScore W4296350897C154945302 @default.
• W4296350897 hasConceptScore W4296350897C162307627 @default.
• W4296350897 hasConceptScore W4296350897C164866538 @default.
• W4296350897 hasConceptScore W4296350897C185798385 @default.
• W4296350897 hasConceptScore W4296350897C190502265 @default.
• W4296350897 hasConceptScore W4296350897C205649164 @default.
• W4296350897 hasConceptScore W4296350897C206729178 @default.
• W4296350897 hasConceptScore W4296350897C21547014 @default.
• W4296350897 hasConceptScore W4296350897C2777211547 @default.
• W4296350897 hasConceptScore W4296350897C2778476105 @default.
• W4296350897 hasConceptScore W4296350897C2992525071 @default.
• W4296350897 hasConceptScore W4296350897C31258907 @default.
• W4296350897 hasConceptScore W4296350897C41008148 @default.
• W4296350897 hasConceptScore W4296350897C50644808 @default.
• W4296350897 hasConceptScore W4296350897C79974875 @default.
• W4296350897 hasConceptScore W4296350897C98045186 @default.
• W4296350897 hasIssue "18" @default.
• W4296350897 hasLocation W42963508971 @default.
• W4296350897 hasLocation W42963508972 @default.
• W4296350897 hasLocation W42963508973 @default.
• W4296350897 hasOpenAccess W4296350897 @default.
• W4296350897 hasPrimaryLocation W42963508971 @default.
• W4296350897 hasRelatedWork W1882733036 @default.
• W4296350897 hasRelatedWork W1992741870 @default.
• W4296350897 hasRelatedWork W2015013785 @default.
• W4296350897 hasRelatedWork W2160425906 @default.
• W4296350897 hasRelatedWork W2429304581 @default.

• next