Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386002421> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4386002421 endingPage "119552" @default.
- W4386002421 startingPage "119552" @default.
- W4386002421 abstract "Currently, graph learning models are indispensable tools to help researchers explore graph-structured data. In academia, using sufficient training data to optimize a graph model on a single device is a typical approach for training a capable graph learning model. Due to privacy concerns, however, it is infeasible to do so in real-world scenarios. Federated learning provides a practical means of addressing this limitation by introducing various privacy-preserving mechanisms, such as differential privacy (DP) on the graph edges. However, although DP in federated graph learning can ensure the security of sensitive information represented in graphs, it usually causes the performance of graph learning models to degrade. In this paper, we investigate how DP can be implemented on graph edges and observe a performance decrease in our experiments. In addition, we note that DP on graph edges introduces noise that perturbs graph proximity, which is one of the graph augmentations in graph contrastive learning. Inspired by this, we propose leveraging graph contrastive learning to alleviate the performance drop resulting from DP. Extensive experiments conducted with four representative graph models on five widely used benchmark datasets show that contrastive learning indeed alleviates the models' DP-induced performance drops." @default.
- W4386002421 created "2023-08-20" @default.
- W4386002421 creator A5009606065 @default.
- W4386002421 creator A5022892997 @default.
- W4386002421 creator A5027145178 @default.
- W4386002421 creator A5051512158 @default.
- W4386002421 creator A5090563981 @default.
- W4386002421 date "2023-11-01" @default.
- W4386002421 modified "2023-10-12" @default.
- W4386002421 title "Mitigating the performance sacrifice in DP-satisfied federated settings through graph contrastive learning" @default.
- W4386002421 cites W2145578524 @default.
- W4386002421 cites W2406036028 @default.
- W4386002421 cites W2461470610 @default.
- W4386002421 cites W2461620095 @default.
- W4386002421 cites W3126230197 @default.
- W4386002421 cites W4205228770 @default.
- W4386002421 cites W4220918534 @default.
- W4386002421 cites W4225423421 @default.
- W4386002421 cites W4307295769 @default.
- W4386002421 cites W4311593456 @default.
- W4386002421 cites W4312158512 @default.
- W4386002421 doi "https://doi.org/10.1016/j.ins.2023.119552" @default.
- W4386002421 hasPublicationYear "2023" @default.
- W4386002421 type Work @default.
- W4386002421 citedByCount "0" @default.
- W4386002421 crossrefType "journal-article" @default.
- W4386002421 hasAuthorship W4386002421A5009606065 @default.
- W4386002421 hasAuthorship W4386002421A5022892997 @default.
- W4386002421 hasAuthorship W4386002421A5027145178 @default.
- W4386002421 hasAuthorship W4386002421A5051512158 @default.
- W4386002421 hasAuthorship W4386002421A5090563981 @default.
- W4386002421 hasBestOaLocation W43860024212 @default.
- W4386002421 hasConcept C124101348 @default.
- W4386002421 hasConcept C132525143 @default.
- W4386002421 hasConcept C154945302 @default.
- W4386002421 hasConcept C23130292 @default.
- W4386002421 hasConcept C41008148 @default.
- W4386002421 hasConcept C80444323 @default.
- W4386002421 hasConceptScore W4386002421C124101348 @default.
- W4386002421 hasConceptScore W4386002421C132525143 @default.
- W4386002421 hasConceptScore W4386002421C154945302 @default.
- W4386002421 hasConceptScore W4386002421C23130292 @default.
- W4386002421 hasConceptScore W4386002421C41008148 @default.
- W4386002421 hasConceptScore W4386002421C80444323 @default.
- W4386002421 hasLocation W43860024211 @default.
- W4386002421 hasLocation W43860024212 @default.
- W4386002421 hasOpenAccess W4386002421 @default.
- W4386002421 hasPrimaryLocation W43860024211 @default.
- W4386002421 hasRelatedWork W2315671126 @default.
- W4386002421 hasRelatedWork W2558166297 @default.
- W4386002421 hasRelatedWork W2604501336 @default.
- W4386002421 hasRelatedWork W2734500670 @default.
- W4386002421 hasRelatedWork W2748952813 @default.
- W4386002421 hasRelatedWork W2899084033 @default.
- W4386002421 hasRelatedWork W2949417504 @default.
- W4386002421 hasRelatedWork W2964481303 @default.
- W4386002421 hasRelatedWork W3038283795 @default.
- W4386002421 hasRelatedWork W798507144 @default.
- W4386002421 hasVolume "648" @default.
- W4386002421 isParatext "false" @default.
- W4386002421 isRetracted "false" @default.
- W4386002421 workType "article" @default.