Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385299096> ?p ?o ?g. }
Showing items 1 to 56 of
56
with 100 items per page.
- W4385299096 abstract "Recently, heterogeneous graph contrastive learning has been widely explored as a self-supervised solution for heterogeneous information network embedding. However, based on contrastive learning, most existing graph expansion proposals fail to extract heterogeneous information adequately, and the simple contrastive objective neglects the modelling of the consistency factor among views. In addition, the single criterion of dividing samples makes the problem of sampling bias in contrastive learning obvious. In response to the issues to be solved, we present a multi-scale contrastive learning method (MCLHE) applied to heterogeneous graph embedding. Concretely, we initially set two scales of contrast objectives for cross-schema and cross-view, capturing the consistency factor between complementary information sources. Secondly, we design node-level contrast and graph-level contrast within the contrast objectives, which are combined to convey different granularity of information. Finally, we take into account both structural and feature embedding similarity measures in the sample partitioning process to enhance sampling hardness. Extensive experiments on several public datasets indicate that MCLHE obtains better performance than existing methods." @default.
- W4385299096 created "2023-07-28" @default.
- W4385299096 creator A5054084525 @default.
- W4385299096 creator A5071162590 @default.
- W4385299096 creator A5092410864 @default.
- W4385299096 date "2023-05-26" @default.
- W4385299096 modified "2023-09-27" @default.
- W4385299096 title "Multi-Scale Contrastive Learning Based Heterogeneous Graph Embedding" @default.
- W4385299096 cites W2911286998 @default.
- W4385299096 cites W2963707260 @default.
- W4385299096 cites W2997686727 @default.
- W4385299096 cites W4226216229 @default.
- W4385299096 doi "https://doi.org/10.1145/3603781.3603823" @default.
- W4385299096 hasPublicationYear "2023" @default.
- W4385299096 type Work @default.
- W4385299096 citedByCount "0" @default.
- W4385299096 crossrefType "proceedings-article" @default.
- W4385299096 hasAuthorship W4385299096A5054084525 @default.
- W4385299096 hasAuthorship W4385299096A5071162590 @default.
- W4385299096 hasAuthorship W4385299096A5092410864 @default.
- W4385299096 hasConcept C111919701 @default.
- W4385299096 hasConcept C119857082 @default.
- W4385299096 hasConcept C132525143 @default.
- W4385299096 hasConcept C154945302 @default.
- W4385299096 hasConcept C177774035 @default.
- W4385299096 hasConcept C2776502983 @default.
- W4385299096 hasConcept C41008148 @default.
- W4385299096 hasConcept C41608201 @default.
- W4385299096 hasConcept C52146309 @default.
- W4385299096 hasConcept C80444323 @default.
- W4385299096 hasConceptScore W4385299096C111919701 @default.
- W4385299096 hasConceptScore W4385299096C119857082 @default.
- W4385299096 hasConceptScore W4385299096C132525143 @default.
- W4385299096 hasConceptScore W4385299096C154945302 @default.
- W4385299096 hasConceptScore W4385299096C177774035 @default.
- W4385299096 hasConceptScore W4385299096C2776502983 @default.
- W4385299096 hasConceptScore W4385299096C41008148 @default.
- W4385299096 hasConceptScore W4385299096C41608201 @default.
- W4385299096 hasConceptScore W4385299096C52146309 @default.
- W4385299096 hasConceptScore W4385299096C80444323 @default.
- W4385299096 hasLocation W43852990961 @default.
- W4385299096 hasOpenAccess W4385299096 @default.
- W4385299096 hasPrimaryLocation W43852990961 @default.
- W4385299096 hasRelatedWork W2893186803 @default.
- W4385299096 hasRelatedWork W2923818335 @default.
- W4385299096 hasRelatedWork W3035116611 @default.
- W4385299096 hasRelatedWork W3044354590 @default.
- W4385299096 hasRelatedWork W3044604502 @default.
- W4385299096 hasRelatedWork W3094605108 @default.
- W4385299096 hasRelatedWork W4226361842 @default.
- W4385299096 hasRelatedWork W4287710676 @default.
- W4385299096 hasRelatedWork W4287763734 @default.
- W4385299096 hasRelatedWork W4310879833 @default.
- W4385299096 isParatext "false" @default.
- W4385299096 isRetracted "false" @default.
- W4385299096 workType "article" @default.