Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328105084> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4328105084 endingPage "110490" @default.
- W4328105084 startingPage "110490" @default.
- W4328105084 abstract "Graph neural networks (GNNs) have shown superior performance in learning node representation for various graph inference tasks and play a pivotal role in high-stakes decision scenarios. However, GNNs may magnify the bias in the original data and make discriminatory decisions toward individuals, reducing user trust. Some research advances have been made to improve the individual fairness of GNNs and increase trust. However, they raise privacy issues when the acquired data involves sensitive information. To address this challenge, we propose a GNN privacy protection method called local private feature-individual fairness graph neural network, LPF-IFGNN for node features based on local differential privacy (LDP) that can strike a balance between fairness and privacy. Specially, we propose an LDP mechanism that considers privacy issues in normalization and can compress and perturb features. In addition, we employ a convolution layer that aggregates multi-hop node features using the mean function to denoise and avoid promoting individual fairness about the perturbed features. We consider the situation where node labels are also required to be protected, and we further propose LPL-LPF-IFGNN based on LDP. Experimental results on five real-world datasets show that LPL-LPF-IFGNN outperforms the state-of-the-art fairness baseline by 41.75% on ACC and 5.02% on [email protected] on private data with a feature privacy budget of 1 and a label privacy budget of 0.5. Experiments further indicate that our methods can achieve a good balance between model utility and individual fairness for private node data with LDP guarantees." @default.
- W4328105084 created "2023-03-22" @default.
- W4328105084 creator A5011059738 @default.
- W4328105084 creator A5015299890 @default.
- W4328105084 creator A5019434289 @default.
- W4328105084 creator A5022008175 @default.
- W4328105084 creator A5056465234 @default.
- W4328105084 date "2023-05-01" @default.
- W4328105084 modified "2023-10-15" @default.
- W4328105084 title "Individual fairness for local private graph neural network" @default.
- W4328105084 cites W2116341502 @default.
- W4328105084 cites W2245160765 @default.
- W4328105084 cites W3027472889 @default.
- W4328105084 cites W3103802018 @default.
- W4328105084 cites W3152893301 @default.
- W4328105084 cites W3160872503 @default.
- W4328105084 cites W3198798629 @default.
- W4328105084 cites W4223413649 @default.
- W4328105084 cites W4229029907 @default.
- W4328105084 doi "https://doi.org/10.1016/j.knosys.2023.110490" @default.
- W4328105084 hasPublicationYear "2023" @default.
- W4328105084 type Work @default.
- W4328105084 citedByCount "0" @default.
- W4328105084 crossrefType "journal-article" @default.
- W4328105084 hasAuthorship W4328105084A5011059738 @default.
- W4328105084 hasAuthorship W4328105084A5015299890 @default.
- W4328105084 hasAuthorship W4328105084A5019434289 @default.
- W4328105084 hasAuthorship W4328105084A5022008175 @default.
- W4328105084 hasAuthorship W4328105084A5056465234 @default.
- W4328105084 hasConcept C119857082 @default.
- W4328105084 hasConcept C123201435 @default.
- W4328105084 hasConcept C124101348 @default.
- W4328105084 hasConcept C127413603 @default.
- W4328105084 hasConcept C132525143 @default.
- W4328105084 hasConcept C136886441 @default.
- W4328105084 hasConcept C144024400 @default.
- W4328105084 hasConcept C154945302 @default.
- W4328105084 hasConcept C19165224 @default.
- W4328105084 hasConcept C23130292 @default.
- W4328105084 hasConcept C2776214188 @default.
- W4328105084 hasConcept C38652104 @default.
- W4328105084 hasConcept C41008148 @default.
- W4328105084 hasConcept C62611344 @default.
- W4328105084 hasConcept C66938386 @default.
- W4328105084 hasConcept C80444323 @default.
- W4328105084 hasConcept C99221444 @default.
- W4328105084 hasConceptScore W4328105084C119857082 @default.
- W4328105084 hasConceptScore W4328105084C123201435 @default.
- W4328105084 hasConceptScore W4328105084C124101348 @default.
- W4328105084 hasConceptScore W4328105084C127413603 @default.
- W4328105084 hasConceptScore W4328105084C132525143 @default.
- W4328105084 hasConceptScore W4328105084C136886441 @default.
- W4328105084 hasConceptScore W4328105084C144024400 @default.
- W4328105084 hasConceptScore W4328105084C154945302 @default.
- W4328105084 hasConceptScore W4328105084C19165224 @default.
- W4328105084 hasConceptScore W4328105084C23130292 @default.
- W4328105084 hasConceptScore W4328105084C2776214188 @default.
- W4328105084 hasConceptScore W4328105084C38652104 @default.
- W4328105084 hasConceptScore W4328105084C41008148 @default.
- W4328105084 hasConceptScore W4328105084C62611344 @default.
- W4328105084 hasConceptScore W4328105084C66938386 @default.
- W4328105084 hasConceptScore W4328105084C80444323 @default.
- W4328105084 hasConceptScore W4328105084C99221444 @default.
- W4328105084 hasFunder F4320321001 @default.
- W4328105084 hasLocation W43281050841 @default.
- W4328105084 hasOpenAccess W4328105084 @default.
- W4328105084 hasPrimaryLocation W43281050841 @default.
- W4328105084 hasRelatedWork W1945159329 @default.
- W4328105084 hasRelatedWork W2061784418 @default.
- W4328105084 hasRelatedWork W2776458542 @default.
- W4328105084 hasRelatedWork W3035493623 @default.
- W4328105084 hasRelatedWork W3082340300 @default.
- W4328105084 hasRelatedWork W3118810630 @default.
- W4328105084 hasRelatedWork W3138219915 @default.
- W4328105084 hasRelatedWork W3143560781 @default.
- W4328105084 hasRelatedWork W3217543883 @default.
- W4328105084 hasRelatedWork W4226146800 @default.
- W4328105084 hasVolume "268" @default.
- W4328105084 isParatext "false" @default.
- W4328105084 isRetracted "false" @default.
- W4328105084 workType "article" @default.