Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288049640> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W4288049640 abstract "Knowledge Graph Completion (KGC), can be performed mainly by inferring missing facts from entities and relations already in the knowledge graphs. However, most methods for KGC only focus on modeling undirected or single relational graph data, ignoring semantic information of multiple relations. We argue that information in the directed edge flows bi-directionally and there exists a latent reverse relation for each relation. These latent reverse relations contain additional information for completing knowledge graphs. Thus, in this paper, we propose a novel method called Knowledge Graph Completion based on Multi-relation Graph Attention neTwork (KGC-MGAT) for more accurate knowledge graph completion. We propose a multi-relational graph attention network to embed each triple and its reverse one respectively. Finally, we design a novel optimal objective for training. We conduct extensive experiments, and the results show the superiority of our method." @default.
- W4288049640 created "2022-07-27" @default.
- W4288049640 creator A5044535114 @default.
- W4288049640 date "2022-02-26" @default.
- W4288049640 modified "2023-09-27" @default.
- W4288049640 title "Knowledge Graph Completion Based on Multi-Relation Graph Attention Network" @default.
- W4288049640 cites W2016753842 @default.
- W4288049640 cites W2283196293 @default.
- W4288049640 cites W2600702321 @default.
- W4288049640 cites W2604314403 @default.
- W4288049640 cites W2728059831 @default.
- W4288049640 cites W2950393809 @default.
- W4288049640 cites W2951105272 @default.
- W4288049640 cites W2996899616 @default.
- W4288049640 cites W3103296573 @default.
- W4288049640 cites W3129070541 @default.
- W4288049640 doi "https://doi.org/10.1145/3524383.3524429" @default.
- W4288049640 hasPublicationYear "2022" @default.
- W4288049640 type Work @default.
- W4288049640 citedByCount "1" @default.
- W4288049640 countsByYear W42880496402023 @default.
- W4288049640 crossrefType "proceedings-article" @default.
- W4288049640 hasAuthorship W4288049640A5044535114 @default.
- W4288049640 hasConcept C124101348 @default.
- W4288049640 hasConcept C132525143 @default.
- W4288049640 hasConcept C154945302 @default.
- W4288049640 hasConcept C25343380 @default.
- W4288049640 hasConcept C2987255567 @default.
- W4288049640 hasConcept C41008148 @default.
- W4288049640 hasConcept C80444323 @default.
- W4288049640 hasConceptScore W4288049640C124101348 @default.
- W4288049640 hasConceptScore W4288049640C132525143 @default.
- W4288049640 hasConceptScore W4288049640C154945302 @default.
- W4288049640 hasConceptScore W4288049640C25343380 @default.
- W4288049640 hasConceptScore W4288049640C2987255567 @default.
- W4288049640 hasConceptScore W4288049640C41008148 @default.
- W4288049640 hasConceptScore W4288049640C80444323 @default.
- W4288049640 hasLocation W42880496401 @default.
- W4288049640 hasOpenAccess W4288049640 @default.
- W4288049640 hasPrimaryLocation W42880496401 @default.
- W4288049640 hasRelatedWork W1524858705 @default.
- W4288049640 hasRelatedWork W2793488029 @default.
- W4288049640 hasRelatedWork W2923818335 @default.
- W4288049640 hasRelatedWork W3022243041 @default.
- W4288049640 hasRelatedWork W3044187822 @default.
- W4288049640 hasRelatedWork W4285821569 @default.
- W4288049640 hasRelatedWork W4288083289 @default.
- W4288049640 hasRelatedWork W4307647416 @default.
- W4288049640 hasRelatedWork W4312327654 @default.
- W4288049640 hasRelatedWork W4323362462 @default.
- W4288049640 isParatext "false" @default.
- W4288049640 isRetracted "false" @default.
- W4288049640 workType "article" @default.