Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385215891> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4385215891 endingPage "3182" @default.
- W4385215891 startingPage "3182" @default.
- W4385215891 abstract "Vertical federated learning is designed to protect user privacy by building local models over disparate datasets and transferring intermediate parameters without directly revealing the underlying data. However, the intermediate parameters uploaded by participants may memorize information about the training data. With the recent legislation on the“right to be forgotten”, it is crucial for vertical federated learning systems to have the ability to forget or remove previous training information of any client. For the first time, this work fills in this research gap by proposing a vertical federated unlearning method on logistic regression model. The proposed method is achieved by imposing constraints on intermediate parameters during the training process and then subtracting target client updates from the global model. The proposed method boasts the advantages that it does not need any new clients for training and requires only one extra round of updates to recover the performance of the previous model. Moreover, data-poisoning attacks are introduced to evaluate the effectiveness of the unlearning process. The effectiveness of the method is demonstrated through experiments conducted on four benchmark datasets. Compared to the conventional unlearning by retraining from scratch, the proposed unlearning method has a negligible decrease in accuracy but can improve training efficiency by over 400%." @default.
- W4385215891 created "2023-07-25" @default.
- W4385215891 creator A5023826377 @default.
- W4385215891 creator A5058584916 @default.
- W4385215891 creator A5063664617 @default.
- W4385215891 creator A5069580961 @default.
- W4385215891 creator A5075722123 @default.
- W4385215891 creator A5081768220 @default.
- W4385215891 creator A5089035316 @default.
- W4385215891 date "2023-07-22" @default.
- W4385215891 modified "2023-10-06" @default.
- W4385215891 title "Vertical Federated Unlearning on the Logistic Regression Model" @default.
- W4385215891 cites W1488996941 @default.
- W4385215891 cites W1622263187 @default.
- W4385215891 cites W2001619934 @default.
- W4385215891 cites W2774854434 @default.
- W4385215891 cites W2995191368 @default.
- W4385215891 cites W3087391814 @default.
- W4385215891 cites W3119520312 @default.
- W4385215891 cites W3128515475 @default.
- W4385215891 cites W3136620885 @default.
- W4385215891 cites W3154155772 @default.
- W4385215891 cites W3209576002 @default.
- W4385215891 cites W3213758632 @default.
- W4385215891 cites W3217077457 @default.
- W4385215891 cites W4205884102 @default.
- W4385215891 cites W4286256876 @default.
- W4385215891 cites W4362714589 @default.
- W4385215891 cites W4367046768 @default.
- W4385215891 cites W4380303816 @default.
- W4385215891 cites W4384891029 @default.
- W4385215891 doi "https://doi.org/10.3390/electronics12143182" @default.
- W4385215891 hasPublicationYear "2023" @default.
- W4385215891 type Work @default.
- W4385215891 citedByCount "0" @default.
- W4385215891 crossrefType "journal-article" @default.
- W4385215891 hasAuthorship W4385215891A5023826377 @default.
- W4385215891 hasAuthorship W4385215891A5058584916 @default.
- W4385215891 hasAuthorship W4385215891A5063664617 @default.
- W4385215891 hasAuthorship W4385215891A5069580961 @default.
- W4385215891 hasAuthorship W4385215891A5075722123 @default.
- W4385215891 hasAuthorship W4385215891A5081768220 @default.
- W4385215891 hasAuthorship W4385215891A5089035316 @default.
- W4385215891 hasBestOaLocation W43852158911 @default.
- W4385215891 hasConcept C111919701 @default.
- W4385215891 hasConcept C119857082 @default.
- W4385215891 hasConcept C124101348 @default.
- W4385215891 hasConcept C13280743 @default.
- W4385215891 hasConcept C136764020 @default.
- W4385215891 hasConcept C144133560 @default.
- W4385215891 hasConcept C145420912 @default.
- W4385215891 hasConcept C154945302 @default.
- W4385215891 hasConcept C155202549 @default.
- W4385215891 hasConcept C185798385 @default.
- W4385215891 hasConcept C205649164 @default.
- W4385215891 hasConcept C2778712577 @default.
- W4385215891 hasConcept C30038468 @default.
- W4385215891 hasConcept C33923547 @default.
- W4385215891 hasConcept C41008148 @default.
- W4385215891 hasConcept C71901391 @default.
- W4385215891 hasConcept C98045186 @default.
- W4385215891 hasConceptScore W4385215891C111919701 @default.
- W4385215891 hasConceptScore W4385215891C119857082 @default.
- W4385215891 hasConceptScore W4385215891C124101348 @default.
- W4385215891 hasConceptScore W4385215891C13280743 @default.
- W4385215891 hasConceptScore W4385215891C136764020 @default.
- W4385215891 hasConceptScore W4385215891C144133560 @default.
- W4385215891 hasConceptScore W4385215891C145420912 @default.
- W4385215891 hasConceptScore W4385215891C154945302 @default.
- W4385215891 hasConceptScore W4385215891C155202549 @default.
- W4385215891 hasConceptScore W4385215891C185798385 @default.
- W4385215891 hasConceptScore W4385215891C205649164 @default.
- W4385215891 hasConceptScore W4385215891C2778712577 @default.
- W4385215891 hasConceptScore W4385215891C30038468 @default.
- W4385215891 hasConceptScore W4385215891C33923547 @default.
- W4385215891 hasConceptScore W4385215891C41008148 @default.
- W4385215891 hasConceptScore W4385215891C71901391 @default.
- W4385215891 hasConceptScore W4385215891C98045186 @default.
- W4385215891 hasIssue "14" @default.
- W4385215891 hasLocation W43852158911 @default.
- W4385215891 hasOpenAccess W4385215891 @default.
- W4385215891 hasPrimaryLocation W43852158911 @default.
- W4385215891 hasRelatedWork W112744582 @default.
- W4385215891 hasRelatedWork W1485630101 @default.
- W4385215891 hasRelatedWork W1983811306 @default.
- W4385215891 hasRelatedWork W2006651773 @default.
- W4385215891 hasRelatedWork W2358742051 @default.
- W4385215891 hasRelatedWork W2365093105 @default.
- W4385215891 hasRelatedWork W2498017833 @default.
- W4385215891 hasRelatedWork W2516405122 @default.
- W4385215891 hasRelatedWork W2961085424 @default.
- W4385215891 hasRelatedWork W4306674287 @default.
- W4385215891 hasVolume "12" @default.
- W4385215891 isParatext "false" @default.
- W4385215891 isRetracted "false" @default.
- W4385215891 workType "article" @default.