Matches in SemOpenAlex for { <https://semopenalex.org/work/W4229444900> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4229444900 endingPage "117361" @default.
- W4229444900 startingPage "117361" @default.
- W4229444900 abstract "Many large knowledge graphs are now available and ready to provide semantically structured information that is regarded as an important resource for question answering and decision support tasks. However, they are built on rigid symbolic frameworks which makes them hard to be used in other intelligent systems. Knowledge graph embedding approaches are gaining increasing attention, which embeds symbolic entities and relations into continuous vector spaces. Such graph embeddings are often learned by training a model to distinguish true triples from negative ones. Unfortunately, the negative triples created by replacing their heads or tails with randomly selected entities are easily identified by the model, which makes them insufficient to train useful models. To this end, we propose a method under a generative adversarial architecture to learn graph embeddings, in which a generative network is trained to provide continually improved “plausible” triples whereas a discriminative network learns to distinguish truth triples from the others by competing with the generator in a two-player minimax game. When arriving at a convergence, the generative network recovers the training data and can be used for knowledge graph completion, while the discriminative network is trained to be a good triple classifier. Extensive experiments demonstrate our method can improve multiple graph embedding models with a significant margin on both link prediction and triple classification tasks." @default.
- W4229444900 created "2022-05-11" @default.
- W4229444900 creator A5017835517 @default.
- W4229444900 creator A5030900873 @default.
- W4229444900 creator A5039957347 @default.
- W4229444900 date "2022-10-01" @default.
- W4229444900 modified "2023-09-27" @default.
- W4229444900 title "Learning structured embeddings of knowledge graphs with generative adversarial framework" @default.
- W4229444900 cites W1529533208 @default.
- W4229444900 cites W200741916 @default.
- W4229444900 cites W2016753842 @default.
- W4229444900 cites W2022166150 @default.
- W4229444900 cites W2024165284 @default.
- W4229444900 cites W2029249040 @default.
- W4229444900 cites W2055317074 @default.
- W4229444900 cites W2081580037 @default.
- W4229444900 cites W2094728533 @default.
- W4229444900 cites W2099752825 @default.
- W4229444900 cites W2149956050 @default.
- W4229444900 cites W2157364932 @default.
- W4229444900 cites W2171278097 @default.
- W4229444900 cites W2184957013 @default.
- W4229444900 cites W2247119764 @default.
- W4229444900 cites W2250184916 @default.
- W4229444900 cites W2250342289 @default.
- W4229444900 cites W2250376704 @default.
- W4229444900 cites W2283196293 @default.
- W4229444900 cites W2460319482 @default.
- W4229444900 cites W2514852614 @default.
- W4229444900 cites W2728059831 @default.
- W4229444900 cites W2949182780 @default.
- W4229444900 cites W2963091079 @default.
- W4229444900 cites W2963485453 @default.
- W4229444900 cites W2996775350 @default.
- W4229444900 cites W3035531911 @default.
- W4229444900 cites W3155001903 @default.
- W4229444900 doi "https://doi.org/10.1016/j.eswa.2022.117361" @default.
- W4229444900 hasPublicationYear "2022" @default.
- W4229444900 type Work @default.
- W4229444900 citedByCount "0" @default.
- W4229444900 crossrefType "journal-article" @default.
- W4229444900 hasAuthorship W4229444900A5017835517 @default.
- W4229444900 hasAuthorship W4229444900A5030900873 @default.
- W4229444900 hasAuthorship W4229444900A5039957347 @default.
- W4229444900 hasConcept C119857082 @default.
- W4229444900 hasConcept C132525143 @default.
- W4229444900 hasConcept C154945302 @default.
- W4229444900 hasConcept C39890363 @default.
- W4229444900 hasConcept C41008148 @default.
- W4229444900 hasConcept C41608201 @default.
- W4229444900 hasConcept C75564084 @default.
- W4229444900 hasConcept C80444323 @default.
- W4229444900 hasConcept C95623464 @default.
- W4229444900 hasConcept C97931131 @default.
- W4229444900 hasConceptScore W4229444900C119857082 @default.
- W4229444900 hasConceptScore W4229444900C132525143 @default.
- W4229444900 hasConceptScore W4229444900C154945302 @default.
- W4229444900 hasConceptScore W4229444900C39890363 @default.
- W4229444900 hasConceptScore W4229444900C41008148 @default.
- W4229444900 hasConceptScore W4229444900C41608201 @default.
- W4229444900 hasConceptScore W4229444900C75564084 @default.
- W4229444900 hasConceptScore W4229444900C80444323 @default.
- W4229444900 hasConceptScore W4229444900C95623464 @default.
- W4229444900 hasConceptScore W4229444900C97931131 @default.
- W4229444900 hasFunder F4320321001 @default.
- W4229444900 hasFunder F4320321885 @default.
- W4229444900 hasLocation W42294449001 @default.
- W4229444900 hasOpenAccess W4229444900 @default.
- W4229444900 hasPrimaryLocation W42294449001 @default.
- W4229444900 hasRelatedWork W1576360539 @default.
- W4229444900 hasRelatedWork W2105080633 @default.
- W4229444900 hasRelatedWork W2166704235 @default.
- W4229444900 hasRelatedWork W2944739904 @default.
- W4229444900 hasRelatedWork W3035116611 @default.
- W4229444900 hasRelatedWork W3149439221 @default.
- W4229444900 hasRelatedWork W4283014405 @default.
- W4229444900 hasRelatedWork W4287763734 @default.
- W4229444900 hasRelatedWork W4288357597 @default.
- W4229444900 hasRelatedWork W4310424780 @default.
- W4229444900 hasVolume "204" @default.
- W4229444900 isParatext "false" @default.
- W4229444900 isRetracted "false" @default.
- W4229444900 workType "article" @default.