Matches in SemOpenAlex for { <https://semopenalex.org/work/W4322832284> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4322832284 abstract "Knowledge graph embedding models (KGEMs) are used for various tasks related to knowledge graphs (KGs), including link prediction. They are trained with loss functions that are computed considering a batch of scored triples and their corresponding labels. Traditional approaches consider the label of a triple to be either true or false. However, recent works suggest that all negative triples should not be valued equally. In line with this recent assumption, we posit that negative triples that are semantically valid w.r.t. domain and range constraints might be high-quality negative triples. As such, loss functions should treat them differently from semantically invalid negative ones. To this aim, we propose semantic-driven versions for the three main loss functions for link prediction. In an extensive and controlled experimental setting, we show that the proposed loss functions systematically provide satisfying results on three public benchmark KGs underpinned with different schemas, which demonstrates both the generality and superiority of our proposed approach. In fact, the proposed loss functions do (1) lead to better MRR and Hits@10 values, (2) drive KGEMs towards better semantic awareness as measured by the Sem@K metric. This highlights that semantic information globally improves KGEMs, and thus should be incorporated into loss functions. Domains and ranges of relations being largely available in schema-defined KGs, this makes our approach both beneficial and widely usable in practice." @default.
- W4322832284 created "2023-03-03" @default.
- W4322832284 creator A5026047589 @default.
- W4322832284 creator A5081875083 @default.
- W4322832284 creator A5088952442 @default.
- W4322832284 creator A5088989613 @default.
- W4322832284 date "2023-03-01" @default.
- W4322832284 modified "2023-10-16" @default.
- W4322832284 title "Treat Different Negatives Differently: Enriching Loss Functions with Domain and Range Constraints for Link Prediction" @default.
- W4322832284 doi "https://doi.org/10.48550/arxiv.2303.00286" @default.
- W4322832284 hasPublicationYear "2023" @default.
- W4322832284 type Work @default.
- W4322832284 citedByCount "0" @default.
- W4322832284 crossrefType "posted-content" @default.
- W4322832284 hasAuthorship W4322832284A5026047589 @default.
- W4322832284 hasAuthorship W4322832284A5081875083 @default.
- W4322832284 hasAuthorship W4322832284A5088952442 @default.
- W4322832284 hasAuthorship W4322832284A5088989613 @default.
- W4322832284 hasBestOaLocation W43228322841 @default.
- W4322832284 hasConcept C119857082 @default.
- W4322832284 hasConcept C132525143 @default.
- W4322832284 hasConcept C136764020 @default.
- W4322832284 hasConcept C154945302 @default.
- W4322832284 hasConcept C15744967 @default.
- W4322832284 hasConcept C2778753846 @default.
- W4322832284 hasConcept C2780615836 @default.
- W4322832284 hasConcept C2780767217 @default.
- W4322832284 hasConcept C31258907 @default.
- W4322832284 hasConcept C41008148 @default.
- W4322832284 hasConcept C41608201 @default.
- W4322832284 hasConcept C52146309 @default.
- W4322832284 hasConcept C542102704 @default.
- W4322832284 hasConcept C80444323 @default.
- W4322832284 hasConceptScore W4322832284C119857082 @default.
- W4322832284 hasConceptScore W4322832284C132525143 @default.
- W4322832284 hasConceptScore W4322832284C136764020 @default.
- W4322832284 hasConceptScore W4322832284C154945302 @default.
- W4322832284 hasConceptScore W4322832284C15744967 @default.
- W4322832284 hasConceptScore W4322832284C2778753846 @default.
- W4322832284 hasConceptScore W4322832284C2780615836 @default.
- W4322832284 hasConceptScore W4322832284C2780767217 @default.
- W4322832284 hasConceptScore W4322832284C31258907 @default.
- W4322832284 hasConceptScore W4322832284C41008148 @default.
- W4322832284 hasConceptScore W4322832284C41608201 @default.
- W4322832284 hasConceptScore W4322832284C52146309 @default.
- W4322832284 hasConceptScore W4322832284C542102704 @default.
- W4322832284 hasConceptScore W4322832284C80444323 @default.
- W4322832284 hasLocation W43228322841 @default.
- W4322832284 hasLocation W43228322842 @default.
- W4322832284 hasOpenAccess W4322832284 @default.
- W4322832284 hasPrimaryLocation W43228322841 @default.
- W4322832284 hasRelatedWork W2397316236 @default.
- W4322832284 hasRelatedWork W2893186803 @default.
- W4322832284 hasRelatedWork W2923818335 @default.
- W4322832284 hasRelatedWork W2979603757 @default.
- W4322832284 hasRelatedWork W3035116611 @default.
- W4322832284 hasRelatedWork W3044354590 @default.
- W4322832284 hasRelatedWork W3094605108 @default.
- W4322832284 hasRelatedWork W4226361842 @default.
- W4322832284 hasRelatedWork W4287763734 @default.
- W4322832284 hasRelatedWork W4310879833 @default.
- W4322832284 isParatext "false" @default.
- W4322832284 isRetracted "false" @default.
- W4322832284 workType "article" @default.