Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281389805> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4281389805 abstract "Link prediction is to predict missing relations between entities for Knowledge Graph Completion (KGC). Convolution neural network has been used in much previous work on link prediction to capture fundamental data pattern of knowledge graph. However, because these models use low-dimensional convolution operation, which limits their performance, they learn fewer expressive features. Further more, they do not have the the capability of keeping the translation property of knowledge triplet, which is an important property for knowledge reasoning. Focusing on these problems, we propose Conv3D (3D Convolution Embedding), a neural network model for link prediction that uses 3D convolution. To capture deeper feature interactions in the knowledge graph, we employ 3D convolution instead of shallow 1D or 2D convolution for generating triplet scores. We conduct link prediction experiments on four general datasets (WN18, WN18RR, FB15k, FB15k-237) and get state-of-the-art (SOTA) results on WN18 and WN18RR. We also explore the influence of convolution parameters (reshaping dimension, number of filters, kernel size) on FB15k-237 and obtain quantitative analytical findings." @default.
- W4281389805 created "2022-05-25" @default.
- W4281389805 creator A5031167446 @default.
- W4281389805 creator A5051666209 @default.
- W4281389805 creator A5062897891 @default.
- W4281389805 creator A5073216396 @default.
- W4281389805 date "2022-05-04" @default.
- W4281389805 modified "2023-09-25" @default.
- W4281389805 title "Convolutional 3D Embedding for Knowledge Graph Completion" @default.
- W4281389805 cites W2081580037 @default.
- W4281389805 cites W2094728533 @default.
- W4281389805 cites W2112796928 @default.
- W4281389805 cites W2250184916 @default.
- W4281389805 cites W2604314403 @default.
- W4281389805 cites W2728059831 @default.
- W4281389805 cites W2946476638 @default.
- W4281389805 cites W2997837621 @default.
- W4281389805 doi "https://doi.org/10.1109/cscwd54268.2022.9776151" @default.
- W4281389805 hasPublicationYear "2022" @default.
- W4281389805 type Work @default.
- W4281389805 citedByCount "2" @default.
- W4281389805 countsByYear W42813898052023 @default.
- W4281389805 crossrefType "proceedings-article" @default.
- W4281389805 hasAuthorship W4281389805A5031167446 @default.
- W4281389805 hasAuthorship W4281389805A5051666209 @default.
- W4281389805 hasAuthorship W4281389805A5062897891 @default.
- W4281389805 hasAuthorship W4281389805A5073216396 @default.
- W4281389805 hasConcept C111472728 @default.
- W4281389805 hasConcept C118615104 @default.
- W4281389805 hasConcept C132525143 @default.
- W4281389805 hasConcept C138885662 @default.
- W4281389805 hasConcept C153180895 @default.
- W4281389805 hasConcept C154945302 @default.
- W4281389805 hasConcept C189950617 @default.
- W4281389805 hasConcept C2778753846 @default.
- W4281389805 hasConcept C31258907 @default.
- W4281389805 hasConcept C33923547 @default.
- W4281389805 hasConcept C41008148 @default.
- W4281389805 hasConcept C41608201 @default.
- W4281389805 hasConcept C45347329 @default.
- W4281389805 hasConcept C50644808 @default.
- W4281389805 hasConcept C74193536 @default.
- W4281389805 hasConcept C80444323 @default.
- W4281389805 hasConcept C81363708 @default.
- W4281389805 hasConceptScore W4281389805C111472728 @default.
- W4281389805 hasConceptScore W4281389805C118615104 @default.
- W4281389805 hasConceptScore W4281389805C132525143 @default.
- W4281389805 hasConceptScore W4281389805C138885662 @default.
- W4281389805 hasConceptScore W4281389805C153180895 @default.
- W4281389805 hasConceptScore W4281389805C154945302 @default.
- W4281389805 hasConceptScore W4281389805C189950617 @default.
- W4281389805 hasConceptScore W4281389805C2778753846 @default.
- W4281389805 hasConceptScore W4281389805C31258907 @default.
- W4281389805 hasConceptScore W4281389805C33923547 @default.
- W4281389805 hasConceptScore W4281389805C41008148 @default.
- W4281389805 hasConceptScore W4281389805C41608201 @default.
- W4281389805 hasConceptScore W4281389805C45347329 @default.
- W4281389805 hasConceptScore W4281389805C50644808 @default.
- W4281389805 hasConceptScore W4281389805C74193536 @default.
- W4281389805 hasConceptScore W4281389805C80444323 @default.
- W4281389805 hasConceptScore W4281389805C81363708 @default.
- W4281389805 hasLocation W42813898051 @default.
- W4281389805 hasOpenAccess W4281389805 @default.
- W4281389805 hasPrimaryLocation W42813898051 @default.
- W4281389805 hasRelatedWork W2766634277 @default.
- W4281389805 hasRelatedWork W2767651786 @default.
- W4281389805 hasRelatedWork W2912288872 @default.
- W4281389805 hasRelatedWork W2949189996 @default.
- W4281389805 hasRelatedWork W2959500052 @default.
- W4281389805 hasRelatedWork W3006085271 @default.
- W4281389805 hasRelatedWork W3200060857 @default.
- W4281389805 hasRelatedWork W4310879833 @default.
- W4281389805 hasRelatedWork W4312417841 @default.
- W4281389805 hasRelatedWork W564581980 @default.
- W4281389805 isParatext "false" @default.
- W4281389805 isRetracted "false" @default.
- W4281389805 workType "article" @default.