Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292223630> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4292223630 endingPage "109524" @default.
- W4292223630 startingPage "109524" @default.
- W4292223630 abstract "Large-scale knowledge graphs are usually incomplete. Knowledge graph embedding has achieved encouraging performance in alleviating the incompleteness of knowledge graphs. There are approaches to leverage the multi-modal content, such as text description and images, to improve the performance of knowledge graph embedding. However,due to the heterogeneity across different modalities, current methods are not effective to fuse the multi-modal content and network structure information to learn the embedding. In this work, a dual-track model DuMF for knowledge graph embedding enhancement is proposed. The model includes two tracks to fuse multi-modal content and network structure respectively. In each track, the expressiveness of joint features is improved by the bilinear method, and meanwhile the task-specific important features are learned by deliberate attention. Finally, the fused features are generated by the gating network. To extensively evaluate the model, two challenging datasets are enriched with additional multi-modal data. Experimental results show that DuMF is superior to baselines in link prediction. The flexibility of the model is promising for the further improvement of model performance." @default.
- W4292223630 created "2022-08-18" @default.
- W4292223630 creator A5000677702 @default.
- W4292223630 creator A5022502922 @default.
- W4292223630 creator A5033233243 @default.
- W4292223630 creator A5088091607 @default.
- W4292223630 creator A5091381220 @default.
- W4292223630 date "2022-10-01" @default.
- W4292223630 modified "2023-10-13" @default.
- W4292223630 title "Fusing visual and textual content for knowledge graph embedding via dual-track model" @default.
- W4292223630 cites W2080133951 @default.
- W4292223630 cites W2081580037 @default.
- W4292223630 cites W2112796928 @default.
- W4292223630 cites W2250184916 @default.
- W4292223630 cites W2283196293 @default.
- W4292223630 cites W2499696929 @default.
- W4292223630 cites W2774837955 @default.
- W4292223630 cites W2799103095 @default.
- W4292223630 cites W2944838001 @default.
- W4292223630 cites W2949972983 @default.
- W4292223630 cites W2950457956 @default.
- W4292223630 cites W2951515642 @default.
- W4292223630 cites W2987386900 @default.
- W4292223630 cites W3009860286 @default.
- W4292223630 cites W3120491054 @default.
- W4292223630 cites W3134422801 @default.
- W4292223630 doi "https://doi.org/10.1016/j.asoc.2022.109524" @default.
- W4292223630 hasPublicationYear "2022" @default.
- W4292223630 type Work @default.
- W4292223630 citedByCount "0" @default.
- W4292223630 crossrefType "journal-article" @default.
- W4292223630 hasAuthorship W4292223630A5000677702 @default.
- W4292223630 hasAuthorship W4292223630A5022502922 @default.
- W4292223630 hasAuthorship W4292223630A5033233243 @default.
- W4292223630 hasAuthorship W4292223630A5088091607 @default.
- W4292223630 hasAuthorship W4292223630A5091381220 @default.
- W4292223630 hasConcept C119599485 @default.
- W4292223630 hasConcept C119857082 @default.
- W4292223630 hasConcept C124101348 @default.
- W4292223630 hasConcept C127413603 @default.
- W4292223630 hasConcept C132525143 @default.
- W4292223630 hasConcept C141353440 @default.
- W4292223630 hasConcept C153083717 @default.
- W4292223630 hasConcept C154945302 @default.
- W4292223630 hasConcept C185592680 @default.
- W4292223630 hasConcept C188027245 @default.
- W4292223630 hasConcept C2987255567 @default.
- W4292223630 hasConcept C41008148 @default.
- W4292223630 hasConcept C41608201 @default.
- W4292223630 hasConcept C71139939 @default.
- W4292223630 hasConcept C80444323 @default.
- W4292223630 hasConceptScore W4292223630C119599485 @default.
- W4292223630 hasConceptScore W4292223630C119857082 @default.
- W4292223630 hasConceptScore W4292223630C124101348 @default.
- W4292223630 hasConceptScore W4292223630C127413603 @default.
- W4292223630 hasConceptScore W4292223630C132525143 @default.
- W4292223630 hasConceptScore W4292223630C141353440 @default.
- W4292223630 hasConceptScore W4292223630C153083717 @default.
- W4292223630 hasConceptScore W4292223630C154945302 @default.
- W4292223630 hasConceptScore W4292223630C185592680 @default.
- W4292223630 hasConceptScore W4292223630C188027245 @default.
- W4292223630 hasConceptScore W4292223630C2987255567 @default.
- W4292223630 hasConceptScore W4292223630C41008148 @default.
- W4292223630 hasConceptScore W4292223630C41608201 @default.
- W4292223630 hasConceptScore W4292223630C71139939 @default.
- W4292223630 hasConceptScore W4292223630C80444323 @default.
- W4292223630 hasFunder F4320321001 @default.
- W4292223630 hasFunder F4320321572 @default.
- W4292223630 hasFunder F4320322919 @default.
- W4292223630 hasFunder F4320331102 @default.
- W4292223630 hasLocation W42922236301 @default.
- W4292223630 hasOpenAccess W4292223630 @default.
- W4292223630 hasPrimaryLocation W42922236301 @default.
- W4292223630 hasRelatedWork W2923818335 @default.
- W4292223630 hasRelatedWork W3105055517 @default.
- W4292223630 hasRelatedWork W3207813134 @default.
- W4292223630 hasRelatedWork W4226361842 @default.
- W4292223630 hasRelatedWork W4295308640 @default.
- W4292223630 hasRelatedWork W4310879833 @default.
- W4292223630 hasRelatedWork W4312327654 @default.
- W4292223630 hasRelatedWork W4312937211 @default.
- W4292223630 hasRelatedWork W4323362462 @default.
- W4292223630 hasRelatedWork W4366999699 @default.
- W4292223630 hasVolume "128" @default.
- W4292223630 isParatext "false" @default.
- W4292223630 isRetracted "false" @default.
- W4292223630 workType "article" @default.