Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385484805> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4385484805 abstract "Few-shot knowledge graph completion (FKGC), which aims to infer missing facts about a relation from only a few reference triples, has recently attracted great attention. The core of solving the FKGC task is to learn a vector representation for each few-shot relation using the corresponding entity represen-tations. To this end, existing models generally enhance entity representations with their direct neighbors. However, a large number of entities have few direct neighbors. Hence, encoding only direct neighborhood is insufficient to obtain satisfactory en-tity representations. In addition, current models typically utilize static embeddings to represent entities, ignoring their diverse semantics, i.e., an entity may show distinct semantics within different few-shot relations. To address these issues, we propose a new FKGC framework, namely TransD-based Multi-hop Meta Learning (TDML). TDML consists of three main components: a multi-hop neighbor encoder to enhance entity representations by aggregating heterogeneous multi-hop neighbors, a transformer encoder to generate the relation meta representations, and a TransD-based relation representation updater that allows each entity to exhibit relation-specific semantics and tune the relation meta representations. Extensive experiments on two public datasets demonstrate that our model outperforms state-of-the-art FKGC methods." @default.
- W4385484805 created "2023-08-03" @default.
- W4385484805 creator A5004318102 @default.
- W4385484805 creator A5018273640 @default.
- W4385484805 creator A5051857716 @default.
- W4385484805 creator A5058743657 @default.
- W4385484805 date "2023-06-18" @default.
- W4385484805 modified "2023-09-23" @default.
- W4385484805 title "TransD-based Multi-hop Meta Learning for Few-shot Knowledge Graph Completion" @default.
- W4385484805 cites W2022166150 @default.
- W4385484805 cites W2080133951 @default.
- W4385484805 cites W2081580037 @default.
- W4385484805 cites W2184957013 @default.
- W4385484805 cites W2250342289 @default.
- W4385484805 cites W2250635077 @default.
- W4385484805 cites W2283196293 @default.
- W4385484805 cites W2728059831 @default.
- W4385484805 cites W2774837955 @default.
- W4385484805 cites W2889234142 @default.
- W4385484805 cites W2912351665 @default.
- W4385484805 cites W2951105272 @default.
- W4385484805 cites W2962886429 @default.
- W4385484805 cites W2971167006 @default.
- W4385484805 cites W2997062749 @default.
- W4385484805 cites W2997738974 @default.
- W4385484805 cites W3034862985 @default.
- W4385484805 cites W3084874487 @default.
- W4385484805 cites W3100606581 @default.
- W4385484805 cites W3155775551 @default.
- W4385484805 cites W3177331119 @default.
- W4385484805 cites W3188999884 @default.
- W4385484805 cites W3202473058 @default.
- W4385484805 cites W4281768843 @default.
- W4385484805 doi "https://doi.org/10.1109/ijcnn54540.2023.10191162" @default.
- W4385484805 hasPublicationYear "2023" @default.
- W4385484805 type Work @default.
- W4385484805 citedByCount "0" @default.
- W4385484805 crossrefType "proceedings-article" @default.
- W4385484805 hasAuthorship W4385484805A5004318102 @default.
- W4385484805 hasAuthorship W4385484805A5018273640 @default.
- W4385484805 hasAuthorship W4385484805A5051857716 @default.
- W4385484805 hasAuthorship W4385484805A5058743657 @default.
- W4385484805 hasConcept C111919701 @default.
- W4385484805 hasConcept C118505674 @default.
- W4385484805 hasConcept C121332964 @default.
- W4385484805 hasConcept C124101348 @default.
- W4385484805 hasConcept C132525143 @default.
- W4385484805 hasConcept C154945302 @default.
- W4385484805 hasConcept C165801399 @default.
- W4385484805 hasConcept C184337299 @default.
- W4385484805 hasConcept C199360897 @default.
- W4385484805 hasConcept C25343380 @default.
- W4385484805 hasConcept C2987255567 @default.
- W4385484805 hasConcept C41008148 @default.
- W4385484805 hasConcept C59404180 @default.
- W4385484805 hasConcept C62520636 @default.
- W4385484805 hasConcept C66322947 @default.
- W4385484805 hasConcept C80444323 @default.
- W4385484805 hasConceptScore W4385484805C111919701 @default.
- W4385484805 hasConceptScore W4385484805C118505674 @default.
- W4385484805 hasConceptScore W4385484805C121332964 @default.
- W4385484805 hasConceptScore W4385484805C124101348 @default.
- W4385484805 hasConceptScore W4385484805C132525143 @default.
- W4385484805 hasConceptScore W4385484805C154945302 @default.
- W4385484805 hasConceptScore W4385484805C165801399 @default.
- W4385484805 hasConceptScore W4385484805C184337299 @default.
- W4385484805 hasConceptScore W4385484805C199360897 @default.
- W4385484805 hasConceptScore W4385484805C25343380 @default.
- W4385484805 hasConceptScore W4385484805C2987255567 @default.
- W4385484805 hasConceptScore W4385484805C41008148 @default.
- W4385484805 hasConceptScore W4385484805C59404180 @default.
- W4385484805 hasConceptScore W4385484805C62520636 @default.
- W4385484805 hasConceptScore W4385484805C66322947 @default.
- W4385484805 hasConceptScore W4385484805C80444323 @default.
- W4385484805 hasFunder F4320335777 @default.
- W4385484805 hasLocation W43854848051 @default.
- W4385484805 hasOpenAccess W4385484805 @default.
- W4385484805 hasPrimaryLocation W43854848051 @default.
- W4385484805 hasRelatedWork W2793488029 @default.
- W4385484805 hasRelatedWork W2804057010 @default.
- W4385484805 hasRelatedWork W2981861606 @default.
- W4385484805 hasRelatedWork W2982223350 @default.
- W4385484805 hasRelatedWork W3014537556 @default.
- W4385484805 hasRelatedWork W3044860086 @default.
- W4385484805 hasRelatedWork W3185716600 @default.
- W4385484805 hasRelatedWork W4285821569 @default.
- W4385484805 hasRelatedWork W4307647416 @default.
- W4385484805 hasRelatedWork W4318148049 @default.
- W4385484805 isParatext "false" @default.
- W4385484805 isRetracted "false" @default.
- W4385484805 workType "article" @default.