Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386002793> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4386002793 endingPage "128" @default.
- W4386002793 startingPage "118" @default.
- W4386002793 abstract "Recently, deep clustering has been extensively employed for various data mining tasks, and it can be divided into auto-encoder (AE)-based and graph neural networks (GNN)-based methods. However, existing AE-based methods fall short in effectively extracting structural information, while GNN suffer from smoothing and heterophily. Although methods that combine AE and GNN achieve impressive performance, there remains an inadequate balance between preserving the raw structure and exploring the underlying structure. Accordingly, we propose a novel network named Structure-Aware Deep Clustering network (SADC). Firstly, we compute the cumulative influence of non-adjacent nodes at multiple depths and, thus, enhance the adjacency matrix. Secondly, an enhanced graph auto-encoder is designed. Thirdly, the latent space of AE is endowed with the ability to perceive the raw structure during the learning process. Besides, we design self-supervised mechanisms to achieve co-optimization of node representation learning and topology learning. A new loss function is designed to preserve the inherent structure while also allowing for exploration of latent data structure. Extensive experiments on six benchmark datasets validate that our method outperforms state-of-the-art methods." @default.
- W4386002793 created "2023-08-20" @default.
- W4386002793 creator A5004580967 @default.
- W4386002793 creator A5037107376 @default.
- W4386002793 creator A5050519902 @default.
- W4386002793 creator A5056660190 @default.
- W4386002793 creator A5056904374 @default.
- W4386002793 creator A5086235570 @default.
- W4386002793 creator A5089971531 @default.
- W4386002793 date "2023-10-01" @default.
- W4386002793 modified "2023-10-18" @default.
- W4386002793 title "Structure-aware deep clustering network based on contrastive learning" @default.
- W4386002793 cites W1997004122 @default.
- W4386002793 cites W2082940153 @default.
- W4386002793 cites W2100495367 @default.
- W4386002793 cites W2113289980 @default.
- W4386002793 cites W2162630660 @default.
- W4386002793 cites W2884851420 @default.
- W4386002793 cites W2898991651 @default.
- W4386002793 cites W2920712697 @default.
- W4386002793 cites W2980008268 @default.
- W4386002793 cites W3101709902 @default.
- W4386002793 cites W4288073539 @default.
- W4386002793 cites W4308045218 @default.
- W4386002793 cites W4323306087 @default.
- W4386002793 cites W4366525308 @default.
- W4386002793 cites W4376865402 @default.
- W4386002793 doi "https://doi.org/10.1016/j.neunet.2023.08.020" @default.
- W4386002793 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37657251" @default.
- W4386002793 hasPublicationYear "2023" @default.
- W4386002793 type Work @default.
- W4386002793 citedByCount "0" @default.
- W4386002793 crossrefType "journal-article" @default.
- W4386002793 hasAuthorship W4386002793A5004580967 @default.
- W4386002793 hasAuthorship W4386002793A5037107376 @default.
- W4386002793 hasAuthorship W4386002793A5050519902 @default.
- W4386002793 hasAuthorship W4386002793A5056660190 @default.
- W4386002793 hasAuthorship W4386002793A5056904374 @default.
- W4386002793 hasAuthorship W4386002793A5086235570 @default.
- W4386002793 hasAuthorship W4386002793A5089971531 @default.
- W4386002793 hasConcept C108583219 @default.
- W4386002793 hasConcept C110484373 @default.
- W4386002793 hasConcept C11413529 @default.
- W4386002793 hasConcept C119857082 @default.
- W4386002793 hasConcept C124101348 @default.
- W4386002793 hasConcept C132525143 @default.
- W4386002793 hasConcept C153180895 @default.
- W4386002793 hasConcept C154945302 @default.
- W4386002793 hasConcept C180356752 @default.
- W4386002793 hasConcept C31972630 @default.
- W4386002793 hasConcept C3770464 @default.
- W4386002793 hasConcept C41008148 @default.
- W4386002793 hasConcept C59404180 @default.
- W4386002793 hasConcept C73555534 @default.
- W4386002793 hasConcept C80444323 @default.
- W4386002793 hasConceptScore W4386002793C108583219 @default.
- W4386002793 hasConceptScore W4386002793C110484373 @default.
- W4386002793 hasConceptScore W4386002793C11413529 @default.
- W4386002793 hasConceptScore W4386002793C119857082 @default.
- W4386002793 hasConceptScore W4386002793C124101348 @default.
- W4386002793 hasConceptScore W4386002793C132525143 @default.
- W4386002793 hasConceptScore W4386002793C153180895 @default.
- W4386002793 hasConceptScore W4386002793C154945302 @default.
- W4386002793 hasConceptScore W4386002793C180356752 @default.
- W4386002793 hasConceptScore W4386002793C31972630 @default.
- W4386002793 hasConceptScore W4386002793C3770464 @default.
- W4386002793 hasConceptScore W4386002793C41008148 @default.
- W4386002793 hasConceptScore W4386002793C59404180 @default.
- W4386002793 hasConceptScore W4386002793C73555534 @default.
- W4386002793 hasConceptScore W4386002793C80444323 @default.
- W4386002793 hasLocation W43860027931 @default.
- W4386002793 hasLocation W43860027932 @default.
- W4386002793 hasOpenAccess W4386002793 @default.
- W4386002793 hasPrimaryLocation W43860027931 @default.
- W4386002793 hasRelatedWork W125803343 @default.
- W4386002793 hasRelatedWork W1991172810 @default.
- W4386002793 hasRelatedWork W2059018062 @default.
- W4386002793 hasRelatedWork W2087456716 @default.
- W4386002793 hasRelatedWork W2369410163 @default.
- W4386002793 hasRelatedWork W2564285047 @default.
- W4386002793 hasRelatedWork W2604585036 @default.
- W4386002793 hasRelatedWork W2982430984 @default.
- W4386002793 hasRelatedWork W4213150077 @default.
- W4386002793 hasRelatedWork W4280593160 @default.
- W4386002793 hasVolume "167" @default.
- W4386002793 isParatext "false" @default.
- W4386002793 isRetracted "false" @default.
- W4386002793 workType "article" @default.