Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386736985> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4386736985 endingPage "8" @default.
- W4386736985 startingPage "1" @default.
- W4386736985 abstract "Deep neural networks (DNN) have demonstrated unprecedented success for various applications. However, due to the issue of limited dataset availability and the strict legal and ethical requirements for data privacy protection, the broad applications of DNN (e.g., medical imaging classification) with large-scale training data have been largely hindered, greatly constraining the model generalization capability. In this paper, we aim to tackle this problem by developing the privacy-preserving constrained domain generalization method, aiming to improve the generalization capability under the privacy-preserving condition. In particular, we propose to improve the information aggregation process on the centralized server side with a novel gradient alignment loss, expecting that the trained model can be better generalized to the “unseen” but related data. The rationale and effectiveness of our proposed method can be explained by connecting our proposed method with the Maximum Mean Discrepancy (MMD) which has been widely adopted as the distribution distance measure. Experimental results on three domain generalization benchmark datasets indicate that our method can achieve better cross-domain generalization capability compared to the state-of-the-art federated learning methods." @default.
- W4386736985 created "2023-09-15" @default.
- W4386736985 creator A5035182164 @default.
- W4386736985 creator A5040091210 @default.
- W4386736985 creator A5042401810 @default.
- W4386736985 creator A5084858586 @default.
- W4386736985 date "2023-01-01" @default.
- W4386736985 modified "2023-09-27" @default.
- W4386736985 title "Privacy-Preserving Constrained Domain Generalization via Gradient Alignment" @default.
- W4386736985 doi "https://doi.org/10.1109/tkde.2023.3315279" @default.
- W4386736985 hasPublicationYear "2023" @default.
- W4386736985 type Work @default.
- W4386736985 citedByCount "0" @default.
- W4386736985 crossrefType "journal-article" @default.
- W4386736985 hasAuthorship W4386736985A5035182164 @default.
- W4386736985 hasAuthorship W4386736985A5040091210 @default.
- W4386736985 hasAuthorship W4386736985A5042401810 @default.
- W4386736985 hasAuthorship W4386736985A5084858586 @default.
- W4386736985 hasConcept C108583219 @default.
- W4386736985 hasConcept C111919701 @default.
- W4386736985 hasConcept C119857082 @default.
- W4386736985 hasConcept C123201435 @default.
- W4386736985 hasConcept C124101348 @default.
- W4386736985 hasConcept C13280743 @default.
- W4386736985 hasConcept C134306372 @default.
- W4386736985 hasConcept C154945302 @default.
- W4386736985 hasConcept C177148314 @default.
- W4386736985 hasConcept C185798385 @default.
- W4386736985 hasConcept C205649164 @default.
- W4386736985 hasConcept C33923547 @default.
- W4386736985 hasConcept C36503486 @default.
- W4386736985 hasConcept C38652104 @default.
- W4386736985 hasConcept C41008148 @default.
- W4386736985 hasConcept C98045186 @default.
- W4386736985 hasConceptScore W4386736985C108583219 @default.
- W4386736985 hasConceptScore W4386736985C111919701 @default.
- W4386736985 hasConceptScore W4386736985C119857082 @default.
- W4386736985 hasConceptScore W4386736985C123201435 @default.
- W4386736985 hasConceptScore W4386736985C124101348 @default.
- W4386736985 hasConceptScore W4386736985C13280743 @default.
- W4386736985 hasConceptScore W4386736985C134306372 @default.
- W4386736985 hasConceptScore W4386736985C154945302 @default.
- W4386736985 hasConceptScore W4386736985C177148314 @default.
- W4386736985 hasConceptScore W4386736985C185798385 @default.
- W4386736985 hasConceptScore W4386736985C205649164 @default.
- W4386736985 hasConceptScore W4386736985C33923547 @default.
- W4386736985 hasConceptScore W4386736985C36503486 @default.
- W4386736985 hasConceptScore W4386736985C38652104 @default.
- W4386736985 hasConceptScore W4386736985C41008148 @default.
- W4386736985 hasConceptScore W4386736985C98045186 @default.
- W4386736985 hasLocation W43867369851 @default.
- W4386736985 hasOpenAccess W4386736985 @default.
- W4386736985 hasPrimaryLocation W43867369851 @default.
- W4386736985 hasRelatedWork W2795261237 @default.
- W4386736985 hasRelatedWork W3014300295 @default.
- W4386736985 hasRelatedWork W3164822677 @default.
- W4386736985 hasRelatedWork W4223943233 @default.
- W4386736985 hasRelatedWork W4225161397 @default.
- W4386736985 hasRelatedWork W4312200629 @default.
- W4386736985 hasRelatedWork W4360585206 @default.
- W4386736985 hasRelatedWork W4364306694 @default.
- W4386736985 hasRelatedWork W4380075502 @default.
- W4386736985 hasRelatedWork W4380086463 @default.
- W4386736985 isParatext "false" @default.
- W4386736985 isRetracted "false" @default.
- W4386736985 workType "article" @default.