Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386329164> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4386329164 abstract "Abstract The development of the Internet and big data has led to the emergence of graphs as an important data representation structure in various real-world scenarios. However, as data size increases, computational complexity and memory requirements pose significant challenges for graph embedding. To address this challenge, this paper proposes a multilevel embedding refinement framework (MERIT) based on large-scale graphs, using spectral distance-constrained graph coarsening algorithms and an improved graph convolutional neural network model that addresses the over-smoothing problem by incorporating initial values and identity mapping. Experimental results on large-scale datasets demonstrate the effectiveness of MERIT, with an average AUROC score 8% higher than other baseline methods. Moreover, in a node classification task on a large-scale graph with 126,825 nodes and 22,412,658 edges, the framework improves embedding quality while enhancing the runtime by 25 times. The experimental findings highlight the superior efficiency and accuracy of the proposed approach compared to other graph embedding methods." @default.
- W4386329164 created "2023-09-01" @default.
- W4386329164 creator A5018103970 @default.
- W4386329164 creator A5024217969 @default.
- W4386329164 creator A5026641797 @default.
- W4386329164 creator A5030607500 @default.
- W4386329164 date "2023-08-31" @default.
- W4386329164 modified "2023-09-27" @default.
- W4386329164 title "Merit: multi-level graph embedding refinement framework for large-scale graph" @default.
- W4386329164 cites W2102086994 @default.
- W4386329164 cites W2393319904 @default.
- W4386329164 cites W2612872092 @default.
- W4386329164 cites W2700550412 @default.
- W4386329164 cites W2804381853 @default.
- W4386329164 cites W2809583854 @default.
- W4386329164 cites W2953452999 @default.
- W4386329164 cites W2962756421 @default.
- W4386329164 cites W2963224980 @default.
- W4386329164 cites W2963707260 @default.
- W4386329164 cites W2964041447 @default.
- W4386329164 cites W2977933764 @default.
- W4386329164 cites W3003250542 @default.
- W4386329164 cites W3004423099 @default.
- W4386329164 cites W3004615113 @default.
- W4386329164 cites W3008459824 @default.
- W4386329164 cites W3008511893 @default.
- W4386329164 cites W3010556302 @default.
- W4386329164 cites W3043242689 @default.
- W4386329164 cites W3084065946 @default.
- W4386329164 cites W3103868164 @default.
- W4386329164 cites W3104097132 @default.
- W4386329164 cites W3105705953 @default.
- W4386329164 cites W3137987278 @default.
- W4386329164 cites W3145302789 @default.
- W4386329164 cites W3152893301 @default.
- W4386329164 cites W3165608758 @default.
- W4386329164 cites W3177399989 @default.
- W4386329164 cites W3179717385 @default.
- W4386329164 cites W3205247817 @default.
- W4386329164 cites W4226427994 @default.
- W4386329164 cites W4285505260 @default.
- W4386329164 cites W4291474301 @default.
- W4386329164 cites W4311905637 @default.
- W4386329164 doi "https://doi.org/10.1007/s40747-023-01211-3" @default.
- W4386329164 hasPublicationYear "2023" @default.
- W4386329164 type Work @default.
- W4386329164 citedByCount "0" @default.
- W4386329164 crossrefType "journal-article" @default.
- W4386329164 hasAuthorship W4386329164A5018103970 @default.
- W4386329164 hasAuthorship W4386329164A5024217969 @default.
- W4386329164 hasAuthorship W4386329164A5026641797 @default.
- W4386329164 hasAuthorship W4386329164A5030607500 @default.
- W4386329164 hasBestOaLocation W43863291641 @default.
- W4386329164 hasConcept C106937863 @default.
- W4386329164 hasConcept C132525143 @default.
- W4386329164 hasConcept C154945302 @default.
- W4386329164 hasConcept C31972630 @default.
- W4386329164 hasConcept C3770464 @default.
- W4386329164 hasConcept C41008148 @default.
- W4386329164 hasConcept C41608201 @default.
- W4386329164 hasConcept C75564084 @default.
- W4386329164 hasConcept C80444323 @default.
- W4386329164 hasConceptScore W4386329164C106937863 @default.
- W4386329164 hasConceptScore W4386329164C132525143 @default.
- W4386329164 hasConceptScore W4386329164C154945302 @default.
- W4386329164 hasConceptScore W4386329164C31972630 @default.
- W4386329164 hasConceptScore W4386329164C3770464 @default.
- W4386329164 hasConceptScore W4386329164C41008148 @default.
- W4386329164 hasConceptScore W4386329164C41608201 @default.
- W4386329164 hasConceptScore W4386329164C75564084 @default.
- W4386329164 hasConceptScore W4386329164C80444323 @default.
- W4386329164 hasFunder F4320321001 @default.
- W4386329164 hasFunder F4320324174 @default.
- W4386329164 hasLocation W43863291641 @default.
- W4386329164 hasOpenAccess W4386329164 @default.
- W4386329164 hasPrimaryLocation W43863291641 @default.
- W4386329164 hasRelatedWork W2893186803 @default.
- W4386329164 hasRelatedWork W2923818335 @default.
- W4386329164 hasRelatedWork W3035116611 @default.
- W4386329164 hasRelatedWork W3044354590 @default.
- W4386329164 hasRelatedWork W3094605108 @default.
- W4386329164 hasRelatedWork W3120440802 @default.
- W4386329164 hasRelatedWork W4212923699 @default.
- W4386329164 hasRelatedWork W4226361842 @default.
- W4386329164 hasRelatedWork W4287763734 @default.
- W4386329164 hasRelatedWork W4310879833 @default.
- W4386329164 isParatext "false" @default.
- W4386329164 isRetracted "false" @default.
- W4386329164 workType "article" @default.