Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283730841> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4283730841 endingPage "21" @default.
- W4283730841 startingPage "1" @default.
- W4283730841 abstract "Knowledge graphs often suffer from incompleteness, and knowledge graph completion (KGC) aims at inferring the missing triplets through knowledge graph embedding from known factual triplets. However, most existing knowledge graph embedding methods only use the relational information of knowledge graph and treat the entities and relations as IDs with simple embedding layer, ignoring the multi-modal information among triplets, such as text descriptions, images, etc. In this work, we propose a novel network to incorporate different modal information with graph structure information for more precise representation of multi-modal knowledge graph, termed as hyper-node relational graph attention (HRGAT) network. In HRGAT, we use low-rank multi-modal fusion to model the intra-modality and inter-modality dynamics, which transforms the original knowledge graph to a hyper-node graph. Then, relational graph attention (RGAT) network is used, which contains relation-specific attention and entity-relation fusion operation to capture the graph structure information. Finally, we aggregate the updated multi-modal information and graph structure information to generate the final embeddings of knowledge graph to achieve KGC. By exploring multi-modal information and graph structure information, HRGAT embraces faster convergence speed and achieves the state-of-the-art for KGC on the standard datasets. Implementation code is available at https://github.com/broliang/HRGAT." @default.
- W4283730841 created "2022-07-01" @default.
- W4283730841 creator A5016843517 @default.
- W4283730841 creator A5072350518 @default.
- W4283730841 creator A5078874629 @default.
- W4283730841 creator A5081872546 @default.
- W4283730841 date "2023-02-06" @default.
- W4283730841 modified "2023-10-13" @default.
- W4283730841 title "Hyper-node Relational Graph Attention Network for Multi-modal Knowledge Graph Completion" @default.
- W4283730841 cites W2016753842 @default.
- W4283730841 cites W2022166150 @default.
- W4283730841 cites W2080133951 @default.
- W4283730841 cites W2094728533 @default.
- W4283730841 cites W2250184916 @default.
- W4283730841 cites W2910396842 @default.
- W4283730841 cites W2963606508 @default.
- W4283730841 cites W2970641574 @default.
- W4283730841 cites W2982244969 @default.
- W4283730841 cites W3038934320 @default.
- W4283730841 cites W3093392043 @default.
- W4283730841 cites W3093922720 @default.
- W4283730841 cites W3103296573 @default.
- W4283730841 cites W3127552693 @default.
- W4283730841 cites W3172478280 @default.
- W4283730841 cites W3184298948 @default.
- W4283730841 cites W3185106195 @default.
- W4283730841 cites W3187974408 @default.
- W4283730841 cites W4206136286 @default.
- W4283730841 doi "https://doi.org/10.1145/3545573" @default.
- W4283730841 hasPublicationYear "2023" @default.
- W4283730841 type Work @default.
- W4283730841 citedByCount "3" @default.
- W4283730841 countsByYear W42837308412023 @default.
- W4283730841 crossrefType "journal-article" @default.
- W4283730841 hasAuthorship W4283730841A5016843517 @default.
- W4283730841 hasAuthorship W4283730841A5072350518 @default.
- W4283730841 hasAuthorship W4283730841A5078874629 @default.
- W4283730841 hasAuthorship W4283730841A5081872546 @default.
- W4283730841 hasConcept C132525143 @default.
- W4283730841 hasConcept C154945302 @default.
- W4283730841 hasConcept C176225458 @default.
- W4283730841 hasConcept C185592680 @default.
- W4283730841 hasConcept C188027245 @default.
- W4283730841 hasConcept C203776342 @default.
- W4283730841 hasConcept C22149727 @default.
- W4283730841 hasConcept C41008148 @default.
- W4283730841 hasConcept C41608201 @default.
- W4283730841 hasConcept C64339825 @default.
- W4283730841 hasConcept C71139939 @default.
- W4283730841 hasConcept C80444323 @default.
- W4283730841 hasConceptScore W4283730841C132525143 @default.
- W4283730841 hasConceptScore W4283730841C154945302 @default.
- W4283730841 hasConceptScore W4283730841C176225458 @default.
- W4283730841 hasConceptScore W4283730841C185592680 @default.
- W4283730841 hasConceptScore W4283730841C188027245 @default.
- W4283730841 hasConceptScore W4283730841C203776342 @default.
- W4283730841 hasConceptScore W4283730841C22149727 @default.
- W4283730841 hasConceptScore W4283730841C41008148 @default.
- W4283730841 hasConceptScore W4283730841C41608201 @default.
- W4283730841 hasConceptScore W4283730841C64339825 @default.
- W4283730841 hasConceptScore W4283730841C71139939 @default.
- W4283730841 hasConceptScore W4283730841C80444323 @default.
- W4283730841 hasFunder F4320321001 @default.
- W4283730841 hasIssue "2" @default.
- W4283730841 hasLocation W42837308411 @default.
- W4283730841 hasOpenAccess W4283730841 @default.
- W4283730841 hasPrimaryLocation W42837308411 @default.
- W4283730841 hasRelatedWork W1496629129 @default.
- W4283730841 hasRelatedWork W1516486508 @default.
- W4283730841 hasRelatedWork W1619417878 @default.
- W4283730841 hasRelatedWork W2493964934 @default.
- W4283730841 hasRelatedWork W2898162043 @default.
- W4283730841 hasRelatedWork W2972311463 @default.
- W4283730841 hasRelatedWork W3080863854 @default.
- W4283730841 hasRelatedWork W4293160369 @default.
- W4283730841 hasRelatedWork W4366999699 @default.
- W4283730841 hasRelatedWork W3115569142 @default.
- W4283730841 hasVolume "19" @default.
- W4283730841 isParatext "false" @default.
- W4283730841 isRetracted "false" @default.
- W4283730841 workType "article" @default.