Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379034048> ?p ?o ?g. }
- W4379034048 endingPage "2258" @default.
- W4379034048 startingPage "2246" @default.
- W4379034048 abstract "Temporal knowledge graph embedding (TKGE) aims to learn the embedding of entities and relations in a temporal knowledge graph (TKG). Although the previous graph neural networks (GNN) based models have achieved promising results, they cannot directly capture the interactions of multi-facts at different timestamps. To address the above limitation, we propose a time-aware relational graph attention model (TARGAT), which takes the multi-facts at different timestamps as a unified graph. First, we develop a relational generator to dynamically generate a series of time-aware relational message transformation matrices, which jointly models the relations and the timestamp information into a unified way. Then, we apply the generated message transformation matrices to project the neighborhood features into different time-aware spaces and aggregate these neighborhood features to explicitly capture the interactions of multi-facts. Finally, a temporal transformer classifier is applied to learn the representation of the query quadruples and predict the missing entities. The experimental results show that our TARGAT model beats the GNN-based models by a large margin and achieves new state-of-the-art results on four popular benchmark datasets." @default.
- W4379034048 created "2023-06-02" @default.
- W4379034048 creator A5000409439 @default.
- W4379034048 creator A5006250732 @default.
- W4379034048 creator A5007102035 @default.
- W4379034048 creator A5042187368 @default.
- W4379034048 creator A5056642269 @default.
- W4379034048 date "2023-01-01" @default.
- W4379034048 modified "2023-10-14" @default.
- W4379034048 title "TARGAT: A Time-Aware Relational Graph Attention Model for Temporal Knowledge Graph Embedding" @default.
- W4379034048 cites W102708294 @default.
- W4379034048 cites W150699991 @default.
- W4379034048 cites W2081580037 @default.
- W4379034048 cites W2094728533 @default.
- W4379034048 cites W2184957013 @default.
- W4379034048 cites W2250342289 @default.
- W4379034048 cites W2283196293 @default.
- W4379034048 cites W2468628149 @default.
- W4379034048 cites W2523679382 @default.
- W4379034048 cites W2604314403 @default.
- W4379034048 cites W2725006314 @default.
- W4379034048 cites W2728059831 @default.
- W4379034048 cites W2756822826 @default.
- W4379034048 cites W2774837955 @default.
- W4379034048 cites W2798864014 @default.
- W4379034048 cites W2889782235 @default.
- W4379034048 cites W2890410208 @default.
- W4379034048 cites W2912860574 @default.
- W4379034048 cites W2949972983 @default.
- W4379034048 cites W2950393809 @default.
- W4379034048 cites W2951515642 @default.
- W4379034048 cites W2953356739 @default.
- W4379034048 cites W2962886429 @default.
- W4379034048 cites W2963490187 @default.
- W4379034048 cites W2966349618 @default.
- W4379034048 cites W2975214639 @default.
- W4379034048 cites W2997837621 @default.
- W4379034048 cites W2998528434 @default.
- W4379034048 cites W3031483194 @default.
- W4379034048 cites W3035707368 @default.
- W4379034048 cites W3057365024 @default.
- W4379034048 cites W3092846532 @default.
- W4379034048 cites W3092995403 @default.
- W4379034048 cites W3093002391 @default.
- W4379034048 cites W3097986917 @default.
- W4379034048 cites W3099150947 @default.
- W4379034048 cites W3099845049 @default.
- W4379034048 cites W3101611558 @default.
- W4379034048 cites W3103296573 @default.
- W4379034048 cites W3113833844 @default.
- W4379034048 cites W3115318530 @default.
- W4379034048 cites W3117206239 @default.
- W4379034048 cites W3152893301 @default.
- W4379034048 cites W3161690523 @default.
- W4379034048 cites W3167316272 @default.
- W4379034048 cites W3169228325 @default.
- W4379034048 cites W3174368915 @default.
- W4379034048 cites W3175405178 @default.
- W4379034048 cites W3182741322 @default.
- W4379034048 cites W3187578449 @default.
- W4379034048 cites W3196669501 @default.
- W4379034048 cites W3199561489 @default.
- W4379034048 cites W4205857559 @default.
- W4379034048 cites W4224910504 @default.
- W4379034048 cites W4226334043 @default.
- W4379034048 cites W4296877272 @default.
- W4379034048 doi "https://doi.org/10.1109/taslp.2023.3282101" @default.
- W4379034048 hasPublicationYear "2023" @default.
- W4379034048 type Work @default.
- W4379034048 citedByCount "0" @default.
- W4379034048 crossrefType "journal-article" @default.
- W4379034048 hasAuthorship W4379034048A5000409439 @default.
- W4379034048 hasAuthorship W4379034048A5006250732 @default.
- W4379034048 hasAuthorship W4379034048A5007102035 @default.
- W4379034048 hasAuthorship W4379034048A5042187368 @default.
- W4379034048 hasAuthorship W4379034048A5056642269 @default.
- W4379034048 hasConcept C113954288 @default.
- W4379034048 hasConcept C119857082 @default.
- W4379034048 hasConcept C124101348 @default.
- W4379034048 hasConcept C132525143 @default.
- W4379034048 hasConcept C154945302 @default.
- W4379034048 hasConcept C177877439 @default.
- W4379034048 hasConcept C38652104 @default.
- W4379034048 hasConcept C41008148 @default.
- W4379034048 hasConcept C41608201 @default.
- W4379034048 hasConcept C5655090 @default.
- W4379034048 hasConcept C75564084 @default.
- W4379034048 hasConcept C77277458 @default.
- W4379034048 hasConcept C80444323 @default.
- W4379034048 hasConceptScore W4379034048C113954288 @default.
- W4379034048 hasConceptScore W4379034048C119857082 @default.
- W4379034048 hasConceptScore W4379034048C124101348 @default.
- W4379034048 hasConceptScore W4379034048C132525143 @default.
- W4379034048 hasConceptScore W4379034048C154945302 @default.
- W4379034048 hasConceptScore W4379034048C177877439 @default.
- W4379034048 hasConceptScore W4379034048C38652104 @default.
- W4379034048 hasConceptScore W4379034048C41008148 @default.
- W4379034048 hasConceptScore W4379034048C41608201 @default.