Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380551475> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4380551475 abstract "This paper presents a personalized graph federated learning (PGFL) framework in which distributedly connected servers and their respective edge devices collaboratively learn device or cluster-specific models while maintaining the privacy of every individual device. The proposed approach exploits similarities among different models to provide a more relevant experience for each device, even in situations with diverse data distributions and disproportionate datasets. Furthermore, to ensure a secure and efficient approach to collaborative personalized learning, we study a variant of the PGFL implementation that utilizes differential privacy, specifically zero-concentrated differential privacy, where a noise sequence perturbs model exchanges. Our mathematical analysis shows that the proposed privacy-preserving PGFL algorithm converges to the optimal cluster-specific solution for each cluster in linear time. It also shows that exploiting similarities among clusters leads to an alternative output whose distance to the original solution is bounded, and that this bound can be adjusted by modifying the algorithm's hyperparameters. Further, our analysis shows that the algorithm ensures local differential privacy for all clients in terms of zero-concentrated differential privacy. Finally, the performance of the proposed PGFL algorithm is examined by performing numerical experiments in the context of regression and classification using synthetic data and the MNIST dataset." @default.
- W4380551475 created "2023-06-14" @default.
- W4380551475 creator A5007045916 @default.
- W4380551475 creator A5009304223 @default.
- W4380551475 creator A5020019430 @default.
- W4380551475 creator A5059938646 @default.
- W4380551475 creator A5082804113 @default.
- W4380551475 date "2023-06-10" @default.
- W4380551475 modified "2023-10-18" @default.
- W4380551475 title "Personalized Graph Federated Learning with Differential Privacy" @default.
- W4380551475 doi "https://doi.org/10.48550/arxiv.2306.06399" @default.
- W4380551475 hasPublicationYear "2023" @default.
- W4380551475 type Work @default.
- W4380551475 citedByCount "0" @default.
- W4380551475 crossrefType "posted-content" @default.
- W4380551475 hasAuthorship W4380551475A5007045916 @default.
- W4380551475 hasAuthorship W4380551475A5009304223 @default.
- W4380551475 hasAuthorship W4380551475A5020019430 @default.
- W4380551475 hasAuthorship W4380551475A5059938646 @default.
- W4380551475 hasAuthorship W4380551475A5082804113 @default.
- W4380551475 hasBestOaLocation W43805514751 @default.
- W4380551475 hasConcept C108583219 @default.
- W4380551475 hasConcept C119857082 @default.
- W4380551475 hasConcept C124101348 @default.
- W4380551475 hasConcept C132525143 @default.
- W4380551475 hasConcept C134306372 @default.
- W4380551475 hasConcept C151730666 @default.
- W4380551475 hasConcept C190502265 @default.
- W4380551475 hasConcept C23130292 @default.
- W4380551475 hasConcept C2779343474 @default.
- W4380551475 hasConcept C33923547 @default.
- W4380551475 hasConcept C34388435 @default.
- W4380551475 hasConcept C41008148 @default.
- W4380551475 hasConcept C73555534 @default.
- W4380551475 hasConcept C80444323 @default.
- W4380551475 hasConcept C86803240 @default.
- W4380551475 hasConceptScore W4380551475C108583219 @default.
- W4380551475 hasConceptScore W4380551475C119857082 @default.
- W4380551475 hasConceptScore W4380551475C124101348 @default.
- W4380551475 hasConceptScore W4380551475C132525143 @default.
- W4380551475 hasConceptScore W4380551475C134306372 @default.
- W4380551475 hasConceptScore W4380551475C151730666 @default.
- W4380551475 hasConceptScore W4380551475C190502265 @default.
- W4380551475 hasConceptScore W4380551475C23130292 @default.
- W4380551475 hasConceptScore W4380551475C2779343474 @default.
- W4380551475 hasConceptScore W4380551475C33923547 @default.
- W4380551475 hasConceptScore W4380551475C34388435 @default.
- W4380551475 hasConceptScore W4380551475C41008148 @default.
- W4380551475 hasConceptScore W4380551475C73555534 @default.
- W4380551475 hasConceptScore W4380551475C80444323 @default.
- W4380551475 hasConceptScore W4380551475C86803240 @default.
- W4380551475 hasLocation W43805514751 @default.
- W4380551475 hasOpenAccess W4380551475 @default.
- W4380551475 hasPrimaryLocation W43805514751 @default.
- W4380551475 hasRelatedWork W2061784418 @default.
- W4380551475 hasRelatedWork W2463477646 @default.
- W4380551475 hasRelatedWork W2620459435 @default.
- W4380551475 hasRelatedWork W3129936541 @default.
- W4380551475 hasRelatedWork W3137448188 @default.
- W4380551475 hasRelatedWork W4213215331 @default.
- W4380551475 hasRelatedWork W4283689893 @default.
- W4380551475 hasRelatedWork W4288055350 @default.
- W4380551475 hasRelatedWork W4313254805 @default.
- W4380551475 hasRelatedWork W3129961329 @default.
- W4380551475 isParatext "false" @default.
- W4380551475 isRetracted "false" @default.
- W4380551475 workType "article" @default.