Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292267086> ?p ?o ?g. }
- W4292267086 endingPage "154" @default.
- W4292267086 startingPage "144" @default.
- W4292267086 abstract "Structural deep clustering involves the use of neural networks for fusing semantic and structural representations for clustering tasks, and it has been receiving increasing attention. In some pioneering works, auto-encoder (AE)-specific representations were integrated with a graph convolutional network (GCN)-specific representation by delivering semantic information to the GCN module layer-by-layer. Although promising performance has been achieved in various applications, we observed that a vital aspect was overlooked in these works: the structural information may vanish in the learning process because of the over-smoothing problem of the GCN module, leading to non-representative features and, thus, deteriorating clustering performance. In this study, we address this issue by proposing a structure enhanced deep clustering network. The GCN-specific structural data representation is enhanced and supervised by its structural information. Specifically, the GCN-specific structural data representation is strengthened during the learning process by combining it with a structure enhanced semantic (SES) representation. A novel structure enhanced AE, named the weighted neighbourhood AE (wNAE), is employed to learn the SES representation for each data sample. Finally, we design a joint supervision strategy to uniformly guide the simultaneous learning of the wNAE and GCN modules and the clustering assignment. Experimental results for different datasets empirically validate the importance of semantic and neighbour-wise structure learning." @default.
- W4292267086 created "2022-08-19" @default.
- W4292267086 creator A5043572903 @default.
- W4292267086 creator A5044103045 @default.
- W4292267086 creator A5064140041 @default.
- W4292267086 creator A5080045592 @default.
- W4292267086 creator A5086333944 @default.
- W4292267086 date "2022-11-01" @default.
- W4292267086 modified "2023-10-13" @default.
- W4292267086 title "Structure enhanced deep clustering network via a weighted neighbourhood auto-encoder" @default.
- W4292267086 cites W2116341502 @default.
- W4292267086 cites W2251410829 @default.
- W4292267086 cites W2608862709 @default.
- W4292267086 cites W2803696107 @default.
- W4292267086 cites W2949911880 @default.
- W4292267086 cites W2950777612 @default.
- W4292267086 cites W2953791858 @default.
- W4292267086 cites W2962852342 @default.
- W4292267086 cites W2963683498 @default.
- W4292267086 cites W2965857891 @default.
- W4292267086 cites W2982225079 @default.
- W4292267086 cites W3026387016 @default.
- W4292267086 cites W3040359118 @default.
- W4292267086 cites W3043995487 @default.
- W4292267086 cites W3101709902 @default.
- W4292267086 doi "https://doi.org/10.1016/j.neunet.2022.08.006" @default.
- W4292267086 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36057181" @default.
- W4292267086 hasPublicationYear "2022" @default.
- W4292267086 type Work @default.
- W4292267086 citedByCount "8" @default.
- W4292267086 countsByYear W42922670862022 @default.
- W4292267086 countsByYear W42922670862023 @default.
- W4292267086 crossrefType "journal-article" @default.
- W4292267086 hasAuthorship W4292267086A5043572903 @default.
- W4292267086 hasAuthorship W4292267086A5044103045 @default.
- W4292267086 hasAuthorship W4292267086A5064140041 @default.
- W4292267086 hasAuthorship W4292267086A5080045592 @default.
- W4292267086 hasAuthorship W4292267086A5086333944 @default.
- W4292267086 hasConcept C101738243 @default.
- W4292267086 hasConcept C108583219 @default.
- W4292267086 hasConcept C111919701 @default.
- W4292267086 hasConcept C118505674 @default.
- W4292267086 hasConcept C119857082 @default.
- W4292267086 hasConcept C124101348 @default.
- W4292267086 hasConcept C132525143 @default.
- W4292267086 hasConcept C134306372 @default.
- W4292267086 hasConcept C153180895 @default.
- W4292267086 hasConcept C154945302 @default.
- W4292267086 hasConcept C161677786 @default.
- W4292267086 hasConcept C17744445 @default.
- W4292267086 hasConcept C199539241 @default.
- W4292267086 hasConcept C2776359362 @default.
- W4292267086 hasConcept C31972630 @default.
- W4292267086 hasConcept C33923547 @default.
- W4292267086 hasConcept C3770464 @default.
- W4292267086 hasConcept C41008148 @default.
- W4292267086 hasConcept C59404180 @default.
- W4292267086 hasConcept C73555534 @default.
- W4292267086 hasConcept C80444323 @default.
- W4292267086 hasConcept C81363708 @default.
- W4292267086 hasConcept C94625758 @default.
- W4292267086 hasConceptScore W4292267086C101738243 @default.
- W4292267086 hasConceptScore W4292267086C108583219 @default.
- W4292267086 hasConceptScore W4292267086C111919701 @default.
- W4292267086 hasConceptScore W4292267086C118505674 @default.
- W4292267086 hasConceptScore W4292267086C119857082 @default.
- W4292267086 hasConceptScore W4292267086C124101348 @default.
- W4292267086 hasConceptScore W4292267086C132525143 @default.
- W4292267086 hasConceptScore W4292267086C134306372 @default.
- W4292267086 hasConceptScore W4292267086C153180895 @default.
- W4292267086 hasConceptScore W4292267086C154945302 @default.
- W4292267086 hasConceptScore W4292267086C161677786 @default.
- W4292267086 hasConceptScore W4292267086C17744445 @default.
- W4292267086 hasConceptScore W4292267086C199539241 @default.
- W4292267086 hasConceptScore W4292267086C2776359362 @default.
- W4292267086 hasConceptScore W4292267086C31972630 @default.
- W4292267086 hasConceptScore W4292267086C33923547 @default.
- W4292267086 hasConceptScore W4292267086C3770464 @default.
- W4292267086 hasConceptScore W4292267086C41008148 @default.
- W4292267086 hasConceptScore W4292267086C59404180 @default.
- W4292267086 hasConceptScore W4292267086C73555534 @default.
- W4292267086 hasConceptScore W4292267086C80444323 @default.
- W4292267086 hasConceptScore W4292267086C81363708 @default.
- W4292267086 hasConceptScore W4292267086C94625758 @default.
- W4292267086 hasFunder F4320321001 @default.
- W4292267086 hasLocation W42922670861 @default.
- W4292267086 hasLocation W42922670862 @default.
- W4292267086 hasOpenAccess W4292267086 @default.
- W4292267086 hasPrimaryLocation W42922670861 @default.
- W4292267086 hasRelatedWork W2292254049 @default.
- W4292267086 hasRelatedWork W2530216401 @default.
- W4292267086 hasRelatedWork W2592385986 @default.
- W4292267086 hasRelatedWork W2784313445 @default.
- W4292267086 hasRelatedWork W2998168123 @default.
- W4292267086 hasRelatedWork W3165463024 @default.
- W4292267086 hasRelatedWork W4221144353 @default.
- W4292267086 hasRelatedWork W4287178339 @default.
- W4292267086 hasRelatedWork W4287995534 @default.