Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306798662> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4306798662 abstract "Federated Learning (FL) is a machine learning paradigm where many local nodes collaboratively train a central model while keeping the training data decentralized. This is particularly relevant for clinical applications since patient data are usually not allowed to be transferred out of medical facilities, leading to the need for FL. Existing FL methods typically share model parameters or employ co-distillation to address the issue of unbalanced data distribution. However, they also require numerous rounds of synchronized communication and, more importantly, suffer from a privacy leakage risk. We propose a privacy-preserving FL framework leveraging unlabeled public data for one-way offline knowledge distillation in this work. The central model is learned from local knowledge via ensemble attention distillation. Our technique uses decentralized and heterogeneous local data like existing FL approaches, but more importantly, it significantly reduces the risk of privacy leakage. We demonstrate that our method achieves very competitive performance with more robust privacy preservation based on extensive experiments on image classification, segmentation, and reconstruction tasks." @default.
- W4306798662 created "2022-10-20" @default.
- W4306798662 creator A5002650791 @default.
- W4306798662 creator A5003798053 @default.
- W4306798662 creator A5003875781 @default.
- W4306798662 creator A5020642496 @default.
- W4306798662 creator A5022366100 @default.
- W4306798662 creator A5023505442 @default.
- W4306798662 creator A5038526207 @default.
- W4306798662 creator A5068780385 @default.
- W4306798662 creator A5079245916 @default.
- W4306798662 creator A5082810803 @default.
- W4306798662 creator A5085245110 @default.
- W4306798662 date "2022-10-16" @default.
- W4306798662 modified "2023-09-27" @default.
- W4306798662 title "Federated Learning with Privacy-Preserving Ensemble Attention Distillation" @default.
- W4306798662 doi "https://doi.org/10.48550/arxiv.2210.08464" @default.
- W4306798662 hasPublicationYear "2022" @default.
- W4306798662 type Work @default.
- W4306798662 citedByCount "0" @default.
- W4306798662 crossrefType "posted-content" @default.
- W4306798662 hasAuthorship W4306798662A5002650791 @default.
- W4306798662 hasAuthorship W4306798662A5003798053 @default.
- W4306798662 hasAuthorship W4306798662A5003875781 @default.
- W4306798662 hasAuthorship W4306798662A5020642496 @default.
- W4306798662 hasAuthorship W4306798662A5022366100 @default.
- W4306798662 hasAuthorship W4306798662A5023505442 @default.
- W4306798662 hasAuthorship W4306798662A5038526207 @default.
- W4306798662 hasAuthorship W4306798662A5068780385 @default.
- W4306798662 hasAuthorship W4306798662A5079245916 @default.
- W4306798662 hasAuthorship W4306798662A5082810803 @default.
- W4306798662 hasAuthorship W4306798662A5085245110 @default.
- W4306798662 hasBestOaLocation W43067986621 @default.
- W4306798662 hasConcept C119857082 @default.
- W4306798662 hasConcept C123201435 @default.
- W4306798662 hasConcept C124101348 @default.
- W4306798662 hasConcept C154945302 @default.
- W4306798662 hasConcept C178790620 @default.
- W4306798662 hasConcept C185592680 @default.
- W4306798662 hasConcept C204030448 @default.
- W4306798662 hasConcept C2992525071 @default.
- W4306798662 hasConcept C38652104 @default.
- W4306798662 hasConcept C41008148 @default.
- W4306798662 hasConcept C89600930 @default.
- W4306798662 hasConceptScore W4306798662C119857082 @default.
- W4306798662 hasConceptScore W4306798662C123201435 @default.
- W4306798662 hasConceptScore W4306798662C124101348 @default.
- W4306798662 hasConceptScore W4306798662C154945302 @default.
- W4306798662 hasConceptScore W4306798662C178790620 @default.
- W4306798662 hasConceptScore W4306798662C185592680 @default.
- W4306798662 hasConceptScore W4306798662C204030448 @default.
- W4306798662 hasConceptScore W4306798662C2992525071 @default.
- W4306798662 hasConceptScore W4306798662C38652104 @default.
- W4306798662 hasConceptScore W4306798662C41008148 @default.
- W4306798662 hasConceptScore W4306798662C89600930 @default.
- W4306798662 hasLocation W43067986621 @default.
- W4306798662 hasOpenAccess W4306798662 @default.
- W4306798662 hasPrimaryLocation W43067986621 @default.
- W4306798662 hasRelatedWork W2961085424 @default.
- W4306798662 hasRelatedWork W3035453001 @default.
- W4306798662 hasRelatedWork W3105298093 @default.
- W4306798662 hasRelatedWork W3135725834 @default.
- W4306798662 hasRelatedWork W4286629047 @default.
- W4306798662 hasRelatedWork W4306321456 @default.
- W4306798662 hasRelatedWork W4306674287 @default.
- W4306798662 hasRelatedWork W4308216551 @default.
- W4306798662 hasRelatedWork W4364305485 @default.
- W4306798662 hasRelatedWork W4224009465 @default.
- W4306798662 isParatext "false" @default.
- W4306798662 isRetracted "false" @default.
- W4306798662 workType "article" @default.