Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380993672> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4380993672 abstract "Graph Neural Networks (GNNs) have achieved great success in modeling graph-structured data. However, recent works show that GNNs are vulnerable to adversarial attacks which can fool the GNN model to make desired predictions of the attacker. In addition, training data of GNNs can be leaked under membership inference attacks. This largely hinders the adoption of GNNs in high-stake domains such as e-commerce, finance and bioinformatics. Though investigations have been made in conducting robust predictions and protecting membership privacy, they generally fail to simultaneously consider the robustness and membership privacy. Therefore, in this work, we study a novel problem of developing robust and membership privacy-preserving GNNs. Our analysis shows that Information Bottleneck (IB) can help filter out noisy information and regularize the predictions on labeled samples, which can benefit robustness and membership privacy. However, structural noises and lack of labels in node classification challenge the deployment of IB on graph-structured data. To mitigate these issues, we propose a novel graph information bottleneck framework that can alleviate structural noises with neighbor bottleneck. Pseudo labels are also incorporated in the optimization to minimize the gap between the predictions on the labeled set and unlabeled set for membership privacy. Extensive experiments on real-world datasets demonstrate that our method can give robust predictions and simultaneously preserve membership privacy." @default.
- W4380993672 created "2023-06-17" @default.
- W4380993672 creator A5011048500 @default.
- W4380993672 creator A5028075867 @default.
- W4380993672 creator A5034963415 @default.
- W4380993672 creator A5037131575 @default.
- W4380993672 creator A5046719515 @default.
- W4380993672 creator A5070663881 @default.
- W4380993672 creator A5088485347 @default.
- W4380993672 creator A5091395218 @default.
- W4380993672 date "2023-06-14" @default.
- W4380993672 modified "2023-09-25" @default.
- W4380993672 title "A Unified Framework of Graph Information Bottleneck for Robustness and Membership Privacy" @default.
- W4380993672 doi "https://doi.org/10.48550/arxiv.2306.08604" @default.
- W4380993672 hasPublicationYear "2023" @default.
- W4380993672 type Work @default.
- W4380993672 citedByCount "0" @default.
- W4380993672 crossrefType "posted-content" @default.
- W4380993672 hasAuthorship W4380993672A5011048500 @default.
- W4380993672 hasAuthorship W4380993672A5028075867 @default.
- W4380993672 hasAuthorship W4380993672A5034963415 @default.
- W4380993672 hasAuthorship W4380993672A5037131575 @default.
- W4380993672 hasAuthorship W4380993672A5046719515 @default.
- W4380993672 hasAuthorship W4380993672A5070663881 @default.
- W4380993672 hasAuthorship W4380993672A5088485347 @default.
- W4380993672 hasAuthorship W4380993672A5091395218 @default.
- W4380993672 hasBestOaLocation W43809936721 @default.
- W4380993672 hasConcept C104317684 @default.
- W4380993672 hasConcept C119857082 @default.
- W4380993672 hasConcept C124101348 @default.
- W4380993672 hasConcept C132525143 @default.
- W4380993672 hasConcept C137822555 @default.
- W4380993672 hasConcept C149635348 @default.
- W4380993672 hasConcept C154945302 @default.
- W4380993672 hasConcept C185592680 @default.
- W4380993672 hasConcept C2776214188 @default.
- W4380993672 hasConcept C2780513914 @default.
- W4380993672 hasConcept C38652104 @default.
- W4380993672 hasConcept C41008148 @default.
- W4380993672 hasConcept C55493867 @default.
- W4380993672 hasConcept C60008888 @default.
- W4380993672 hasConcept C63479239 @default.
- W4380993672 hasConcept C73555534 @default.
- W4380993672 hasConcept C80444323 @default.
- W4380993672 hasConceptScore W4380993672C104317684 @default.
- W4380993672 hasConceptScore W4380993672C119857082 @default.
- W4380993672 hasConceptScore W4380993672C124101348 @default.
- W4380993672 hasConceptScore W4380993672C132525143 @default.
- W4380993672 hasConceptScore W4380993672C137822555 @default.
- W4380993672 hasConceptScore W4380993672C149635348 @default.
- W4380993672 hasConceptScore W4380993672C154945302 @default.
- W4380993672 hasConceptScore W4380993672C185592680 @default.
- W4380993672 hasConceptScore W4380993672C2776214188 @default.
- W4380993672 hasConceptScore W4380993672C2780513914 @default.
- W4380993672 hasConceptScore W4380993672C38652104 @default.
- W4380993672 hasConceptScore W4380993672C41008148 @default.
- W4380993672 hasConceptScore W4380993672C55493867 @default.
- W4380993672 hasConceptScore W4380993672C60008888 @default.
- W4380993672 hasConceptScore W4380993672C63479239 @default.
- W4380993672 hasConceptScore W4380993672C73555534 @default.
- W4380993672 hasConceptScore W4380993672C80444323 @default.
- W4380993672 hasLocation W43809936721 @default.
- W4380993672 hasOpenAccess W4380993672 @default.
- W4380993672 hasPrimaryLocation W43809936721 @default.
- W4380993672 hasRelatedWork W2001561361 @default.
- W4380993672 hasRelatedWork W3034190530 @default.
- W4380993672 hasRelatedWork W3177538078 @default.
- W4380993672 hasRelatedWork W3179381308 @default.
- W4380993672 hasRelatedWork W4280534256 @default.
- W4380993672 hasRelatedWork W4283321310 @default.
- W4380993672 hasRelatedWork W4307473403 @default.
- W4380993672 hasRelatedWork W4307654699 @default.
- W4380993672 hasRelatedWork W4312225749 @default.
- W4380993672 hasRelatedWork W62276109 @default.
- W4380993672 isParatext "false" @default.
- W4380993672 isRetracted "false" @default.
- W4380993672 workType "article" @default.