Matches in SemOpenAlex for { <https://semopenalex.org/work/W3198512483> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3198512483 endingPage "1" @default.
- W3198512483 startingPage "1" @default.
- W3198512483 abstract "With the rapid development and widespread application of Knowledge graphs (KGs) in many artificial intelligence tasks, a large number of efforts have been made to refine them and increase their quality. Knowedge graph embedding (KGE) has become one of the main refinement tasks, which aims to predict missing facts based on existing ones in KGs. However, there are still mainly two difficult unresolved challenges: (i) how to leverage the local structural features of entities and the potential soft logical rules to learn more expressive embedding of entites and relations; and (ii) how to combine these two learning processes into one unified model. To conquer these problems, we propose a novel KGE model named JSSKGE, which can textbf{J}ointly learn the local textbf{S}tructural features of entities and textbf{S}oft logical rules. Firstly, we employ graph attention networks which are specially designed for graph-structured data to aggregate the local structural information of nodes. Then, we utilize soft logical rules implicated in KGs as an expert to further rectify the embeddings of entities and relations. By jointly learning, we can obtain more informative embeddings to predict new facts. With experiments on four commonly used datasets, the JSSKGE obtains better performance than state-of-the-art approaches." @default.
- W3198512483 created "2021-09-13" @default.
- W3198512483 creator A5026821474 @default.
- W3198512483 creator A5042096631 @default.
- W3198512483 creator A5078083652 @default.
- W3198512483 date "2021-01-01" @default.
- W3198512483 modified "2023-10-02" @default.
- W3198512483 title "Knowledge Graph Completion by Jointly Learning Structural Features and Soft Logical Rules" @default.
- W3198512483 cites W1552847225 @default.
- W3198512483 cites W2022166150 @default.
- W3198512483 cites W2081580037 @default.
- W3198512483 cites W2094728533 @default.
- W3198512483 cites W2107306718 @default.
- W3198512483 cites W2184957013 @default.
- W3198512483 cites W2250635077 @default.
- W3198512483 cites W2251079237 @default.
- W3198512483 cites W2283196293 @default.
- W3198512483 cites W2296268288 @default.
- W3198512483 cites W2300469216 @default.
- W3198512483 cites W2467775179 @default.
- W3198512483 cites W2511805592 @default.
- W3198512483 cites W2563063592 @default.
- W3198512483 cites W2604165577 @default.
- W3198512483 cites W2604314403 @default.
- W3198512483 cites W2728059831 @default.
- W3198512483 cites W2755637027 @default.
- W3198512483 cites W2759136286 @default.
- W3198512483 cites W2927610379 @default.
- W3198512483 cites W2950393809 @default.
- W3198512483 cites W2962834633 @default.
- W3198512483 cites W2963359213 @default.
- W3198512483 cites W2966298461 @default.
- W3198512483 cites W2984661639 @default.
- W3198512483 cites W3099154743 @default.
- W3198512483 cites W651477617 @default.
- W3198512483 doi "https://doi.org/10.1109/tkde.2021.3108224" @default.
- W3198512483 hasPublicationYear "2021" @default.
- W3198512483 type Work @default.
- W3198512483 sameAs 3198512483 @default.
- W3198512483 citedByCount "4" @default.
- W3198512483 countsByYear W31985124832022 @default.
- W3198512483 countsByYear W31985124832023 @default.
- W3198512483 crossrefType "journal-article" @default.
- W3198512483 hasAuthorship W3198512483A5026821474 @default.
- W3198512483 hasAuthorship W3198512483A5042096631 @default.
- W3198512483 hasAuthorship W3198512483A5078083652 @default.
- W3198512483 hasConcept C119857082 @default.
- W3198512483 hasConcept C132525143 @default.
- W3198512483 hasConcept C153083717 @default.
- W3198512483 hasConcept C154945302 @default.
- W3198512483 hasConcept C159985019 @default.
- W3198512483 hasConcept C192562407 @default.
- W3198512483 hasConcept C2987255567 @default.
- W3198512483 hasConcept C41008148 @default.
- W3198512483 hasConcept C41608201 @default.
- W3198512483 hasConcept C4679612 @default.
- W3198512483 hasConcept C80444323 @default.
- W3198512483 hasConceptScore W3198512483C119857082 @default.
- W3198512483 hasConceptScore W3198512483C132525143 @default.
- W3198512483 hasConceptScore W3198512483C153083717 @default.
- W3198512483 hasConceptScore W3198512483C154945302 @default.
- W3198512483 hasConceptScore W3198512483C159985019 @default.
- W3198512483 hasConceptScore W3198512483C192562407 @default.
- W3198512483 hasConceptScore W3198512483C2987255567 @default.
- W3198512483 hasConceptScore W3198512483C41008148 @default.
- W3198512483 hasConceptScore W3198512483C41608201 @default.
- W3198512483 hasConceptScore W3198512483C4679612 @default.
- W3198512483 hasConceptScore W3198512483C80444323 @default.
- W3198512483 hasFunder F4320324116 @default.
- W3198512483 hasLocation W31985124831 @default.
- W3198512483 hasOpenAccess W3198512483 @default.
- W3198512483 hasPrimaryLocation W31985124831 @default.
- W3198512483 hasRelatedWork W2243512948 @default.
- W3198512483 hasRelatedWork W2883748392 @default.
- W3198512483 hasRelatedWork W2923818335 @default.
- W3198512483 hasRelatedWork W4205349486 @default.
- W3198512483 hasRelatedWork W4206547516 @default.
- W3198512483 hasRelatedWork W4226361842 @default.
- W3198512483 hasRelatedWork W4296285654 @default.
- W3198512483 hasRelatedWork W4310879833 @default.
- W3198512483 hasRelatedWork W4385279070 @default.
- W3198512483 hasRelatedWork W3129794543 @default.
- W3198512483 isParatext "false" @default.
- W3198512483 isRetracted "false" @default.
- W3198512483 magId "3198512483" @default.
- W3198512483 workType "article" @default.