Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297088423> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4297088423 endingPage "98500" @default.
- W4297088423 startingPage "98490" @default.
- W4297088423 abstract "Owing to label-free modeling of complex heterogeneity, self-supervised heterogeneous graph representation learning (SS-HGRL) has been widely studied in recent years. The goal of SS-HGRL is to design an unsupervised learning framework to represent complicated heterogeneous graph structures. However, based on contrastive learning, most existing methods of SS-HGRL require a large number of negative samples, which significantly increases the computation and memory costs. Furthermore, many methods cannot fully extract knowledge from a heterogeneous graph. To learn global and local information simultaneously at low time and space costs, we propose a novel Siamese Network based Multi-scale bootstrapping contrastive learning approach for Heterogeneous graphs (SNMH). Specifically, we first obtain views under the meta-path schema and the 1-hop relation type schema through dual-schema view generation. Then, we propose cross-schema and cross-view bootstrapping contrastive objectives to maximize the similarity of node representations between different schemas and views. By integrating and optimizing the above objectives, we can extract local and global information and eventually obtain the node representations for downstream tasks. To demonstrate the effectiveness of our model, we conduct experiments on several public datasets. Experimental results show that our model is superior to the state-of-the-art methods on the premise of lower time and space complexity. The source code and datasets are publicly available at https://github.com/lorisky1214/SNMH." @default.
- W4297088423 created "2022-09-27" @default.
- W4297088423 creator A5001986457 @default.
- W4297088423 creator A5008984910 @default.
- W4297088423 creator A5025739250 @default.
- W4297088423 creator A5028148241 @default.
- W4297088423 creator A5068503490 @default.
- W4297088423 creator A5087387871 @default.
- W4297088423 date "2022-01-01" @default.
- W4297088423 modified "2023-09-30" @default.
- W4297088423 title "Siamese Network Based Multiscale Self-Supervised Heterogeneous Graph Representation Learning" @default.
- W4297088423 cites W103340358 @default.
- W4297088423 cites W2157364932 @default.
- W4297088423 cites W2171590421 @default.
- W4297088423 cites W2533635416 @default.
- W4297088423 cites W2604314403 @default.
- W4297088423 cites W2911286998 @default.
- W4297088423 cites W2962756421 @default.
- W4297088423 cites W2963707260 @default.
- W4297088423 cites W2997686727 @default.
- W4297088423 cites W3004507689 @default.
- W4297088423 cites W3095746859 @default.
- W4297088423 cites W3100330855 @default.
- W4297088423 cites W3100848837 @default.
- W4297088423 cites W3104097132 @default.
- W4297088423 cites W3172710079 @default.
- W4297088423 cites W3176047499 @default.
- W4297088423 cites W3190214286 @default.
- W4297088423 doi "https://doi.org/10.1109/access.2022.3187088" @default.
- W4297088423 hasPublicationYear "2022" @default.
- W4297088423 type Work @default.
- W4297088423 citedByCount "1" @default.
- W4297088423 countsByYear W42970884232023 @default.
- W4297088423 crossrefType "journal-article" @default.
- W4297088423 hasAuthorship W4297088423A5001986457 @default.
- W4297088423 hasAuthorship W4297088423A5008984910 @default.
- W4297088423 hasAuthorship W4297088423A5025739250 @default.
- W4297088423 hasAuthorship W4297088423A5028148241 @default.
- W4297088423 hasAuthorship W4297088423A5068503490 @default.
- W4297088423 hasAuthorship W4297088423A5087387871 @default.
- W4297088423 hasBestOaLocation W42970884231 @default.
- W4297088423 hasConcept C106159729 @default.
- W4297088423 hasConcept C119857082 @default.
- W4297088423 hasConcept C132525143 @default.
- W4297088423 hasConcept C154945302 @default.
- W4297088423 hasConcept C162324750 @default.
- W4297088423 hasConcept C207609745 @default.
- W4297088423 hasConcept C41008148 @default.
- W4297088423 hasConcept C52146309 @default.
- W4297088423 hasConcept C59404180 @default.
- W4297088423 hasConcept C80444323 @default.
- W4297088423 hasConceptScore W4297088423C106159729 @default.
- W4297088423 hasConceptScore W4297088423C119857082 @default.
- W4297088423 hasConceptScore W4297088423C132525143 @default.
- W4297088423 hasConceptScore W4297088423C154945302 @default.
- W4297088423 hasConceptScore W4297088423C162324750 @default.
- W4297088423 hasConceptScore W4297088423C207609745 @default.
- W4297088423 hasConceptScore W4297088423C41008148 @default.
- W4297088423 hasConceptScore W4297088423C52146309 @default.
- W4297088423 hasConceptScore W4297088423C59404180 @default.
- W4297088423 hasConceptScore W4297088423C80444323 @default.
- W4297088423 hasFunder F4320321001 @default.
- W4297088423 hasFunder F4320324174 @default.
- W4297088423 hasLocation W42970884231 @default.
- W4297088423 hasOpenAccess W4297088423 @default.
- W4297088423 hasPrimaryLocation W42970884231 @default.
- W4297088423 hasRelatedWork W2104232660 @default.
- W4297088423 hasRelatedWork W2804057010 @default.
- W4297088423 hasRelatedWork W2961085424 @default.
- W4297088423 hasRelatedWork W2980233312 @default.
- W4297088423 hasRelatedWork W2989955213 @default.
- W4297088423 hasRelatedWork W3087493185 @default.
- W4297088423 hasRelatedWork W3094605108 @default.
- W4297088423 hasRelatedWork W4206762304 @default.
- W4297088423 hasRelatedWork W4307206737 @default.
- W4297088423 hasRelatedWork W4367684998 @default.
- W4297088423 hasVolume "10" @default.
- W4297088423 isParatext "false" @default.
- W4297088423 isRetracted "false" @default.
- W4297088423 workType "article" @default.