Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313127763> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4313127763 abstract "Attributed graph clustering is a fundamental yet challenging task for graph analysis, which is of significance in the real world. Recently, graph contrastive learning have demonstrated excellent performance on clustering task. However, we observe that existing methods have the following three defects: a) an end-to-end graph clustering framework based on contrastive clustering has not yet been implemented, b) they require a pretext task to obtain initial labels, c) and most methods lack a specific loss function for clustering processes. To address above issues, we innovatively propose Attributed Graph Contrastive Clustering (AGCC), which is a novel self-supervised attributed graph clustering framework. AGCC can directly produce a clustering assignment matrix without calculating target distribution matrix. Specifically, in our method, an effective module based on contrastive graph representation learning is being leveraged to extract node embeddings by node features and topological structure. In the phase of data augmentation, the module can adaptively mask node features and drops edges. Meanwhile, another reliable contrastive clustering module generates clustering results through contrasting the representation of each cluster. Comprehensive empirical analysis, compared with various types of classic and deep methods, demonstrates the efficacy and the scalability of the proposed method." @default.
- W4313127763 created "2023-01-06" @default.
- W4313127763 creator A5017947172 @default.
- W4313127763 creator A5021000274 @default.
- W4313127763 creator A5048050496 @default.
- W4313127763 creator A5090335612 @default.
- W4313127763 date "2022-07-18" @default.
- W4313127763 modified "2023-09-28" @default.
- W4313127763 title "Attributed Graph Clustering with Double Contrastive Projector" @default.
- W4313127763 cites W1977556410 @default.
- W4313127763 cites W2021347322 @default.
- W4313127763 cites W2023155726 @default.
- W4313127763 cites W2075150581 @default.
- W4313127763 cites W2088412871 @default.
- W4313127763 cites W2092939357 @default.
- W4313127763 cites W2121947440 @default.
- W4313127763 cites W2122925692 @default.
- W4313127763 cites W2154897810 @default.
- W4313127763 cites W2161984370 @default.
- W4313127763 cites W2217748804 @default.
- W4313127763 cites W2405933695 @default.
- W4313127763 cites W2741943936 @default.
- W4313127763 cites W2769535977 @default.
- W4313127763 cites W2950352474 @default.
- W4313127763 cites W2962756421 @default.
- W4313127763 cites W2972209102 @default.
- W4313127763 cites W3034531178 @default.
- W4313127763 cites W3035524453 @default.
- W4313127763 cites W3087124270 @default.
- W4313127763 cites W3095746859 @default.
- W4313127763 cites W3101709902 @default.
- W4313127763 cites W3104097132 @default.
- W4313127763 cites W3105705953 @default.
- W4313127763 cites W3157127187 @default.
- W4313127763 cites W3188916965 @default.
- W4313127763 doi "https://doi.org/10.1109/ijcnn55064.2022.9892848" @default.
- W4313127763 hasPublicationYear "2022" @default.
- W4313127763 type Work @default.
- W4313127763 citedByCount "0" @default.
- W4313127763 crossrefType "proceedings-article" @default.
- W4313127763 hasAuthorship W4313127763A5017947172 @default.
- W4313127763 hasAuthorship W4313127763A5021000274 @default.
- W4313127763 hasAuthorship W4313127763A5048050496 @default.
- W4313127763 hasAuthorship W4313127763A5090335612 @default.
- W4313127763 hasConcept C124101348 @default.
- W4313127763 hasConcept C132525143 @default.
- W4313127763 hasConcept C153180895 @default.
- W4313127763 hasConcept C154945302 @default.
- W4313127763 hasConcept C22047676 @default.
- W4313127763 hasConcept C41008148 @default.
- W4313127763 hasConcept C48044578 @default.
- W4313127763 hasConcept C59404180 @default.
- W4313127763 hasConcept C73555534 @default.
- W4313127763 hasConcept C77088390 @default.
- W4313127763 hasConcept C80444323 @default.
- W4313127763 hasConcept C94641424 @default.
- W4313127763 hasConceptScore W4313127763C124101348 @default.
- W4313127763 hasConceptScore W4313127763C132525143 @default.
- W4313127763 hasConceptScore W4313127763C153180895 @default.
- W4313127763 hasConceptScore W4313127763C154945302 @default.
- W4313127763 hasConceptScore W4313127763C22047676 @default.
- W4313127763 hasConceptScore W4313127763C41008148 @default.
- W4313127763 hasConceptScore W4313127763C48044578 @default.
- W4313127763 hasConceptScore W4313127763C59404180 @default.
- W4313127763 hasConceptScore W4313127763C73555534 @default.
- W4313127763 hasConceptScore W4313127763C77088390 @default.
- W4313127763 hasConceptScore W4313127763C80444323 @default.
- W4313127763 hasConceptScore W4313127763C94641424 @default.
- W4313127763 hasFunder F4320321001 @default.
- W4313127763 hasLocation W43131277631 @default.
- W4313127763 hasOpenAccess W4313127763 @default.
- W4313127763 hasPrimaryLocation W43131277631 @default.
- W4313127763 hasRelatedWork W2006039862 @default.
- W4313127763 hasRelatedWork W2054781765 @default.
- W4313127763 hasRelatedWork W2085268214 @default.
- W4313127763 hasRelatedWork W2155218858 @default.
- W4313127763 hasRelatedWork W2905576882 @default.
- W4313127763 hasRelatedWork W3175662935 @default.
- W4313127763 hasRelatedWork W3188916965 @default.
- W4313127763 hasRelatedWork W4287702396 @default.
- W4313127763 hasRelatedWork W4309581948 @default.
- W4313127763 hasRelatedWork W4323896988 @default.
- W4313127763 isParatext "false" @default.
- W4313127763 isRetracted "false" @default.
- W4313127763 workType "article" @default.