Matches in SemOpenAlex for { <https://semopenalex.org/work/W3176251287> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3176251287 endingPage "9137" @default.
- W3176251287 startingPage "9128" @default.
- W3176251287 abstract "Knowledge graph builds the bridge from massive data generated by the interaction and communication between various objects to intelligent applications and services in Internet of Things. The graph representation learning technology represented by graph neural networks plays an essential role in the understanding and reasoning of the knowledge graph with complicated internal structure. Although they are capable of assigning different attention weights to neighbors, the graph attention network (GAT) and its variants are inherently flawed and inadequate in modeling high-order knowledge graphs with high heterogeneity. Therefore, we propose a novel multirelational GAT framework in this article for knowledge reasoning over heterogeneous graphs by employing tensor and tensor operations. Specifically, we formulate the general high-order heterogeneous knowledge graph first. Then, the tensor GAT (TGAT), composed of three components: 1) heterogeneous information propagation; 2) multimodal semantic-aware attention; and 3) knowledge aggregation, is developed to simulate rich interactions between mixed triples, entities, and relationships when aggregating local information. What is more, we utilize the Tucker model to compress the parameters of TGAT and further reduce the storage and calculation consumption of the intermediate calculation process on the premise of maintaining the expressive power. We conduct extensive experiments to solve the link prediction task on four real-world heterogeneous graphs, and the results demonstrate that the TGAT model proposed in this article remarkably outperforms state-of-the-art competitors and improves the hits@1 accuracy by up to 7.6%." @default.
- W3176251287 created "2021-07-05" @default.
- W3176251287 creator A5034601329 @default.
- W3176251287 creator A5046138332 @default.
- W3176251287 creator A5049154222 @default.
- W3176251287 creator A5051840260 @default.
- W3176251287 creator A5063525578 @default.
- W3176251287 creator A5086470221 @default.
- W3176251287 date "2022-06-15" @default.
- W3176251287 modified "2023-10-17" @default.
- W3176251287 title "Tensor Graph Attention Network for Knowledge Reasoning in Internet of Things" @default.
- W3176251287 cites W1993482030 @default.
- W3176251287 cites W2013912476 @default.
- W3176251287 cites W2024165284 @default.
- W3176251287 cites W2026892459 @default.
- W3176251287 cites W2125027602 @default.
- W3176251287 cites W2250635077 @default.
- W3176251287 cites W2265347063 @default.
- W3176251287 cites W2774837955 @default.
- W3176251287 cites W2888994561 @default.
- W3176251287 cites W2889344053 @default.
- W3176251287 cites W2945623882 @default.
- W3176251287 cites W2945742688 @default.
- W3176251287 cites W2951105272 @default.
- W3176251287 cites W2954734636 @default.
- W3176251287 cites W2972535098 @default.
- W3176251287 cites W2982407593 @default.
- W3176251287 cites W3015158377 @default.
- W3176251287 cites W3015616869 @default.
- W3176251287 cites W3033675321 @default.
- W3176251287 cites W3081454631 @default.
- W3176251287 cites W3088196840 @default.
- W3176251287 cites W3088609916 @default.
- W3176251287 cites W3089463120 @default.
- W3176251287 cites W3155581945 @default.
- W3176251287 doi "https://doi.org/10.1109/jiot.2021.3092360" @default.
- W3176251287 hasPublicationYear "2022" @default.
- W3176251287 type Work @default.
- W3176251287 sameAs 3176251287 @default.
- W3176251287 citedByCount "1" @default.
- W3176251287 countsByYear W31762512872022 @default.
- W3176251287 crossrefType "journal-article" @default.
- W3176251287 hasAuthorship W3176251287A5034601329 @default.
- W3176251287 hasAuthorship W3176251287A5046138332 @default.
- W3176251287 hasAuthorship W3176251287A5049154222 @default.
- W3176251287 hasAuthorship W3176251287A5051840260 @default.
- W3176251287 hasAuthorship W3176251287A5063525578 @default.
- W3176251287 hasAuthorship W3176251287A5086470221 @default.
- W3176251287 hasConcept C132525143 @default.
- W3176251287 hasConcept C138885662 @default.
- W3176251287 hasConcept C154945302 @default.
- W3176251287 hasConcept C161301231 @default.
- W3176251287 hasConcept C2778023277 @default.
- W3176251287 hasConcept C41008148 @default.
- W3176251287 hasConcept C41895202 @default.
- W3176251287 hasConcept C80444323 @default.
- W3176251287 hasConceptScore W3176251287C132525143 @default.
- W3176251287 hasConceptScore W3176251287C138885662 @default.
- W3176251287 hasConceptScore W3176251287C154945302 @default.
- W3176251287 hasConceptScore W3176251287C161301231 @default.
- W3176251287 hasConceptScore W3176251287C2778023277 @default.
- W3176251287 hasConceptScore W3176251287C41008148 @default.
- W3176251287 hasConceptScore W3176251287C41895202 @default.
- W3176251287 hasConceptScore W3176251287C80444323 @default.
- W3176251287 hasFunder F4320321001 @default.
- W3176251287 hasFunder F4320335777 @default.
- W3176251287 hasIssue "12" @default.
- W3176251287 hasLocation W31762512871 @default.
- W3176251287 hasOpenAccess W3176251287 @default.
- W3176251287 hasPrimaryLocation W31762512871 @default.
- W3176251287 hasRelatedWork W1580720870 @default.
- W3176251287 hasRelatedWork W2026696399 @default.
- W3176251287 hasRelatedWork W2246353450 @default.
- W3176251287 hasRelatedWork W2293509402 @default.
- W3176251287 hasRelatedWork W2597681995 @default.
- W3176251287 hasRelatedWork W2923818335 @default.
- W3176251287 hasRelatedWork W4206939502 @default.
- W3176251287 hasRelatedWork W4288083289 @default.
- W3176251287 hasRelatedWork W4309679315 @default.
- W3176251287 hasRelatedWork W1831144830 @default.
- W3176251287 hasVolume "9" @default.
- W3176251287 isParatext "false" @default.
- W3176251287 isRetracted "false" @default.
- W3176251287 magId "3176251287" @default.
- W3176251287 workType "article" @default.