Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310379539> ?p ?o ?g. }
- W4310379539 endingPage "3958" @default.
- W4310379539 startingPage "3958" @default.
- W4310379539 abstract "Federated learning (FL) aims to address the challenges of data silos and privacy protection in artificial intelligence. Vertically federated learning (VFL) with independent feature spaces and overlapping ID spaces can capture more knowledge and facilitate model learning. However, VFL has both privacy and utility problems in framework construction. On the one hand, sharing gradients may cause privacy leakage. On the other hand, the increase in participants brings a surge in the feature dimension of the global model, which results in higher computation costs and lower model accuracy. To address these issues, we propose a vertically federated learning algorithm with correlated differential privacy (CRDP-FL) to meet FL systems’ privacy and utility requirements. A privacy-preserved VFL framework is designed based on differential privacy (DP) between organizations with many network edge devices. Meanwhile, feature selection is performed to improve the algorithm’s efficiency and model performance to solve the problem of dimensionality explosion. We also propose a quantitative correlation analysis technique for VFL to reduce the correlated sensitivity and noise injection, balancing the utility decline due to DP protection. We theoretically analyze the privacy level and utility of CRDP-FL. A real vertically federated learning scenario is simulated with personalized settings based on the ISOLET and Breast Cancer datasets to verify the method’s effectiveness in model accuracy, privacy budget, and data correlation." @default.
- W4310379539 created "2022-12-10" @default.
- W4310379539 creator A5000544808 @default.
- W4310379539 creator A5012187327 @default.
- W4310379539 creator A5042893723 @default.
- W4310379539 creator A5084630731 @default.
- W4310379539 creator A5086191549 @default.
- W4310379539 date "2022-11-29" @default.
- W4310379539 modified "2023-09-26" @default.
- W4310379539 title "Vertically Federated Learning with Correlated Differential Privacy" @default.
- W4310379539 cites W1676820704 @default.
- W4310379539 cites W1985511977 @default.
- W4310379539 cites W2001347093 @default.
- W4310379539 cites W2054922243 @default.
- W4310379539 cites W2060041315 @default.
- W4310379539 cites W2076826889 @default.
- W4310379539 cites W2085472312 @default.
- W4310379539 cites W2123820077 @default.
- W4310379539 cites W2137351756 @default.
- W4310379539 cites W2595058628 @default.
- W4310379539 cites W2619868737 @default.
- W4310379539 cites W2800017313 @default.
- W4310379539 cites W2859081967 @default.
- W4310379539 cites W2907203011 @default.
- W4310379539 cites W2930926105 @default.
- W4310379539 cites W2963106566 @default.
- W4310379539 cites W2969945192 @default.
- W4310379539 cites W2995191368 @default.
- W4310379539 cites W2998628425 @default.
- W4310379539 cites W3027749727 @default.
- W4310379539 cites W3035053747 @default.
- W4310379539 cites W3096193467 @default.
- W4310379539 cites W3102994281 @default.
- W4310379539 cites W3106284904 @default.
- W4310379539 cites W3111259855 @default.
- W4310379539 cites W3111327456 @default.
- W4310379539 cites W3127040002 @default.
- W4310379539 cites W3162269235 @default.
- W4310379539 cites W3176605771 @default.
- W4310379539 cites W3206162503 @default.
- W4310379539 cites W4205373044 @default.
- W4310379539 cites W4206707323 @default.
- W4310379539 cites W4206912802 @default.
- W4310379539 cites W4212899026 @default.
- W4310379539 cites W4213044365 @default.
- W4310379539 cites W4213420832 @default.
- W4310379539 cites W4294862274 @default.
- W4310379539 cites W4296122895 @default.
- W4310379539 cites W4309284213 @default.
- W4310379539 doi "https://doi.org/10.3390/electronics11233958" @default.
- W4310379539 hasPublicationYear "2022" @default.
- W4310379539 type Work @default.
- W4310379539 citedByCount "0" @default.
- W4310379539 crossrefType "journal-article" @default.
- W4310379539 hasAuthorship W4310379539A5000544808 @default.
- W4310379539 hasAuthorship W4310379539A5012187327 @default.
- W4310379539 hasAuthorship W4310379539A5042893723 @default.
- W4310379539 hasAuthorship W4310379539A5084630731 @default.
- W4310379539 hasAuthorship W4310379539A5086191549 @default.
- W4310379539 hasBestOaLocation W43103795391 @default.
- W4310379539 hasConcept C11413529 @default.
- W4310379539 hasConcept C119857082 @default.
- W4310379539 hasConcept C123201435 @default.
- W4310379539 hasConcept C124101348 @default.
- W4310379539 hasConcept C138885662 @default.
- W4310379539 hasConcept C154945302 @default.
- W4310379539 hasConcept C23130292 @default.
- W4310379539 hasConcept C2776401178 @default.
- W4310379539 hasConcept C2992525071 @default.
- W4310379539 hasConcept C3017597292 @default.
- W4310379539 hasConcept C38652104 @default.
- W4310379539 hasConcept C41008148 @default.
- W4310379539 hasConcept C41895202 @default.
- W4310379539 hasConcept C45374587 @default.
- W4310379539 hasConceptScore W4310379539C11413529 @default.
- W4310379539 hasConceptScore W4310379539C119857082 @default.
- W4310379539 hasConceptScore W4310379539C123201435 @default.
- W4310379539 hasConceptScore W4310379539C124101348 @default.
- W4310379539 hasConceptScore W4310379539C138885662 @default.
- W4310379539 hasConceptScore W4310379539C154945302 @default.
- W4310379539 hasConceptScore W4310379539C23130292 @default.
- W4310379539 hasConceptScore W4310379539C2776401178 @default.
- W4310379539 hasConceptScore W4310379539C2992525071 @default.
- W4310379539 hasConceptScore W4310379539C3017597292 @default.
- W4310379539 hasConceptScore W4310379539C38652104 @default.
- W4310379539 hasConceptScore W4310379539C41008148 @default.
- W4310379539 hasConceptScore W4310379539C41895202 @default.
- W4310379539 hasConceptScore W4310379539C45374587 @default.
- W4310379539 hasIssue "23" @default.
- W4310379539 hasLocation W43103795391 @default.
- W4310379539 hasOpenAccess W4310379539 @default.
- W4310379539 hasPrimaryLocation W43103795391 @default.
- W4310379539 hasRelatedWork W3005947044 @default.
- W4310379539 hasRelatedWork W3116386889 @default.
- W4310379539 hasRelatedWork W4226016526 @default.
- W4310379539 hasRelatedWork W4315630415 @default.
- W4310379539 hasRelatedWork W4315630424 @default.
- W4310379539 hasRelatedWork W4360993981 @default.