Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386804500> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4386804500 endingPage "682" @default.
- W4386804500 startingPage "666" @default.
- W4386804500 abstract "With broad applications in network analysis and mining, Graph Contrastive Learning (GCL) is attracting growing research interest. Despite its successful usage in extracting concise but useful information through contrasting different augmented graph views as an outstanding self-supervised technique, GCL is facing a major challenge in how to make the semantic information extracted well-organized in structure and consequently easily understood by a downstream classifier. In this paper, we propose a novel cluster-based GCL framework to obtain a semantically well-formed structure of node embeddings via maximizing mutual information between input graph and output embeddings, which also provides a more clear decision boundary through accomplishing a cluster-level global-local contrastive task. We further argue in theory that the proposed method can correctly maximize the mutual information between an input graph and output embeddings. Moreover, we further improve the proposed method for better practical performance by incorporating additional refined gadgets, e.g., measuring uncertainty of clustering and additional structural information extraction via local-local node-level contrasting module enhanced by Graph Cut. Lastly, extensive experiments are carried out to demonstrate the practical performance gain of our method in six real-world datasets over the most prevalent existing state-of-the-art models." @default.
- W4386804500 created "2023-09-17" @default.
- W4386804500 creator A5013126405 @default.
- W4386804500 creator A5033922885 @default.
- W4386804500 creator A5051017723 @default.
- W4386804500 creator A5073154896 @default.
- W4386804500 creator A5081623112 @default.
- W4386804500 creator A5081790008 @default.
- W4386804500 creator A5084963725 @default.
- W4386804500 date "2023-01-01" @default.
- W4386804500 modified "2023-09-27" @default.
- W4386804500 title "Graph Contrastive Representation Learning with Input-Aware and Cluster-Aware Regularization" @default.
- W4386804500 cites W2132914434 @default.
- W4386804500 cites W2808409763 @default.
- W4386804500 cites W2981450816 @default.
- W4386804500 cites W3034531178 @default.
- W4386804500 cites W3035739162 @default.
- W4386804500 cites W3104097132 @default.
- W4386804500 cites W3114632476 @default.
- W4386804500 cites W3190214286 @default.
- W4386804500 cites W3207924272 @default.
- W4386804500 cites W4210257598 @default.
- W4386804500 doi "https://doi.org/10.1007/978-3-031-43415-0_39" @default.
- W4386804500 hasPublicationYear "2023" @default.
- W4386804500 type Work @default.
- W4386804500 citedByCount "0" @default.
- W4386804500 crossrefType "book-chapter" @default.
- W4386804500 hasAuthorship W4386804500A5013126405 @default.
- W4386804500 hasAuthorship W4386804500A5033922885 @default.
- W4386804500 hasAuthorship W4386804500A5051017723 @default.
- W4386804500 hasAuthorship W4386804500A5073154896 @default.
- W4386804500 hasAuthorship W4386804500A5081623112 @default.
- W4386804500 hasAuthorship W4386804500A5081790008 @default.
- W4386804500 hasAuthorship W4386804500A5084963725 @default.
- W4386804500 hasConcept C119857082 @default.
- W4386804500 hasConcept C124101348 @default.
- W4386804500 hasConcept C132525143 @default.
- W4386804500 hasConcept C154945302 @default.
- W4386804500 hasConcept C41008148 @default.
- W4386804500 hasConcept C59404180 @default.
- W4386804500 hasConcept C73555534 @default.
- W4386804500 hasConcept C80444323 @default.
- W4386804500 hasConcept C95623464 @default.
- W4386804500 hasConceptScore W4386804500C119857082 @default.
- W4386804500 hasConceptScore W4386804500C124101348 @default.
- W4386804500 hasConceptScore W4386804500C132525143 @default.
- W4386804500 hasConceptScore W4386804500C154945302 @default.
- W4386804500 hasConceptScore W4386804500C41008148 @default.
- W4386804500 hasConceptScore W4386804500C59404180 @default.
- W4386804500 hasConceptScore W4386804500C73555534 @default.
- W4386804500 hasConceptScore W4386804500C80444323 @default.
- W4386804500 hasConceptScore W4386804500C95623464 @default.
- W4386804500 hasLocation W43868045001 @default.
- W4386804500 hasOpenAccess W4386804500 @default.
- W4386804500 hasPrimaryLocation W43868045001 @default.
- W4386804500 hasRelatedWork W2471138382 @default.
- W4386804500 hasRelatedWork W2556319748 @default.
- W4386804500 hasRelatedWork W2804057010 @default.
- W4386804500 hasRelatedWork W2989955213 @default.
- W4386804500 hasRelatedWork W3087493185 @default.
- W4386804500 hasRelatedWork W4200632554 @default.
- W4386804500 hasRelatedWork W4206762304 @default.
- W4386804500 hasRelatedWork W4226127995 @default.
- W4386804500 hasRelatedWork W4312256146 @default.
- W4386804500 hasRelatedWork W4367684998 @default.
- W4386804500 isParatext "false" @default.
- W4386804500 isRetracted "false" @default.
- W4386804500 workType "book-chapter" @default.