Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380091325> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4380091325 endingPage "704" @default.
- W4380091325 startingPage "689" @default.
- W4380091325 abstract "Federated learning (FL) is a promising approach that enables distributed clients to collaboratively train a global model while preserving their data privacy. However, FL often suffers from data heterogeneity problems, which can significantly affect its performance. To address this, clustered federated learning (CFL) has been proposed to construct personalized models for different client clusters. One effective client clustering strategy is to allow clients to choose their own local models from a model pool based on their performance. However, without pre-trained model parameters, such a strategy is prone to clustering failure, in which all clients choose the same model. Unfortunately, collecting a large amount of labeled data for pre-training can be costly and impractical in distributed environments. To overcome this challenge, we leverage self-supervised contrastive learning to exploit unlabeled data for the pre-training of FL systems. Together, self-supervised pre-training and client clustering can be crucial components for tackling the data heterogeneity issues of FL. Leveraging these two crucial strategies, we propose contrastive pre-training-based clustered federated learning (CP-CFL) to improve the model convergence and overall performance of FL systems. In this work, we demonstrate the effectiveness of CP-CFL through extensive experiments in heterogeneous FL settings, and present various interesting observations." @default.
- W4380091325 created "2023-06-10" @default.
- W4380091325 creator A5002774844 @default.
- W4380091325 creator A5003122223 @default.
- W4380091325 creator A5005668963 @default.
- W4380091325 creator A5040105725 @default.
- W4380091325 creator A5062638357 @default.
- W4380091325 date "2023-08-01" @default.
- W4380091325 modified "2023-09-24" @default.
- W4380091325 title "Contrastive encoder pre-training-based clustered federated learning for heterogeneous data" @default.
- W4380091325 cites W2025768430 @default.
- W4380091325 cites W2112796928 @default.
- W4380091325 cites W2194775991 @default.
- W4380091325 cites W2963420272 @default.
- W4380091325 cites W2989289980 @default.
- W4380091325 cites W3026182744 @default.
- W4380091325 cites W3033511014 @default.
- W4380091325 cites W3034781633 @default.
- W4380091325 cites W3080934299 @default.
- W4380091325 cites W3081178085 @default.
- W4380091325 cites W3099980742 @default.
- W4380091325 cites W3107887114 @default.
- W4380091325 cites W3123599388 @default.
- W4380091325 cites W3134944578 @default.
- W4380091325 cites W3145385912 @default.
- W4380091325 cites W3171007011 @default.
- W4380091325 cites W3176780013 @default.
- W4380091325 cites W3182158470 @default.
- W4380091325 cites W3193756050 @default.
- W4380091325 cites W3198939852 @default.
- W4380091325 cites W4220779061 @default.
- W4380091325 cites W4226142397 @default.
- W4380091325 cites W4281753687 @default.
- W4380091325 cites W4285242894 @default.
- W4380091325 cites W4285327149 @default.
- W4380091325 cites W4289841367 @default.
- W4380091325 cites W4303578704 @default.
- W4380091325 cites W4312352414 @default.
- W4380091325 cites W4312462223 @default.
- W4380091325 cites W4327927980 @default.
- W4380091325 doi "https://doi.org/10.1016/j.neunet.2023.06.010" @default.
- W4380091325 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37385023" @default.
- W4380091325 hasPublicationYear "2023" @default.
- W4380091325 type Work @default.
- W4380091325 citedByCount "0" @default.
- W4380091325 crossrefType "journal-article" @default.
- W4380091325 hasAuthorship W4380091325A5002774844 @default.
- W4380091325 hasAuthorship W4380091325A5003122223 @default.
- W4380091325 hasAuthorship W4380091325A5005668963 @default.
- W4380091325 hasAuthorship W4380091325A5040105725 @default.
- W4380091325 hasAuthorship W4380091325A5062638357 @default.
- W4380091325 hasConcept C111919701 @default.
- W4380091325 hasConcept C118505674 @default.
- W4380091325 hasConcept C119857082 @default.
- W4380091325 hasConcept C124101348 @default.
- W4380091325 hasConcept C153083717 @default.
- W4380091325 hasConcept C154945302 @default.
- W4380091325 hasConcept C165696696 @default.
- W4380091325 hasConcept C199360897 @default.
- W4380091325 hasConcept C2780801425 @default.
- W4380091325 hasConcept C2992525071 @default.
- W4380091325 hasConcept C38652104 @default.
- W4380091325 hasConcept C41008148 @default.
- W4380091325 hasConcept C73555534 @default.
- W4380091325 hasConceptScore W4380091325C111919701 @default.
- W4380091325 hasConceptScore W4380091325C118505674 @default.
- W4380091325 hasConceptScore W4380091325C119857082 @default.
- W4380091325 hasConceptScore W4380091325C124101348 @default.
- W4380091325 hasConceptScore W4380091325C153083717 @default.
- W4380091325 hasConceptScore W4380091325C154945302 @default.
- W4380091325 hasConceptScore W4380091325C165696696 @default.
- W4380091325 hasConceptScore W4380091325C199360897 @default.
- W4380091325 hasConceptScore W4380091325C2780801425 @default.
- W4380091325 hasConceptScore W4380091325C2992525071 @default.
- W4380091325 hasConceptScore W4380091325C38652104 @default.
- W4380091325 hasConceptScore W4380091325C41008148 @default.
- W4380091325 hasConceptScore W4380091325C73555534 @default.
- W4380091325 hasFunder F4320322120 @default.
- W4380091325 hasLocation W43800913251 @default.
- W4380091325 hasLocation W43800913252 @default.
- W4380091325 hasOpenAccess W4380091325 @default.
- W4380091325 hasPrimaryLocation W43800913251 @default.
- W4380091325 hasRelatedWork W2135486170 @default.
- W4380091325 hasRelatedWork W2275988210 @default.
- W4380091325 hasRelatedWork W2331043530 @default.
- W4380091325 hasRelatedWork W2374725260 @default.
- W4380091325 hasRelatedWork W2393933887 @default.
- W4380091325 hasRelatedWork W2798029542 @default.
- W4380091325 hasRelatedWork W2961085424 @default.
- W4380091325 hasRelatedWork W2997512100 @default.
- W4380091325 hasRelatedWork W4306674287 @default.
- W4380091325 hasRelatedWork W4361193208 @default.
- W4380091325 hasVolume "165" @default.
- W4380091325 isParatext "false" @default.
- W4380091325 isRetracted "false" @default.
- W4380091325 workType "article" @default.