Matches in SemOpenAlex for { <https://semopenalex.org/work/W4368348057> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4368348057 endingPage "100394" @default.
- W4368348057 startingPage "100394" @default.
- W4368348057 abstract "As artificial intelligence gradually steps into cognitive intelligence stage, knowledge graphs (KGs) play an increasingly important role in many natural language processing tasks. Due to the prevalence of long-tail relations in KGs, few-shot knowledge graph completion (KGC) for link prediction of long-tail relations has gradually become a hot research topic. Current few-shot KGC methods mainly focus on the static representation of surrounding entities to explore the potential semantic features of entities, while ignoring the dynamic properties among entities and the special influence of the long-tail relation on link prediction. In this paper, a new meta-learning based dynamic adaptive relation learning model (DARL) is proposed for few-shot KGC. For obtaining better semantic information of the meta knowledge, the proposed DARL model applies a dynamic neighbor encoder to incorporate neighbor relations into entity embedding. In addition, DARL builds attention mechanism based fusion strategy for different attributes of the same relation to further enhance the relation-meta learning ability. We evaluate our DARL model on two public benchmark datasets NELL-One and WIKI-One for link prediction. Extensive experimental results indicate that our DARL outperforms the state-of-the-art models with an average relative improvement about 23.37%, 32.46% in MRR and Hits@1 on NELL-One, respectively." @default.
- W4368348057 created "2023-05-05" @default.
- W4368348057 creator A5009976811 @default.
- W4368348057 creator A5030184407 @default.
- W4368348057 creator A5047604818 @default.
- W4368348057 creator A5057414572 @default.
- W4368348057 date "2023-08-01" @default.
- W4368348057 modified "2023-09-27" @default.
- W4368348057 title "Meta-Learning Based Dynamic Adaptive Relation Learning for Few-Shot Knowledge Graph Completion" @default.
- W4368348057 cites W2044803677 @default.
- W4368348057 cites W2080133951 @default.
- W4368348057 cites W2759136286 @default.
- W4368348057 cites W2948271276 @default.
- W4368348057 cites W2969314833 @default.
- W4368348057 cites W3003265726 @default.
- W4368348057 cites W3107691142 @default.
- W4368348057 cites W3176529699 @default.
- W4368348057 cites W3180352486 @default.
- W4368348057 cites W3183320130 @default.
- W4368348057 cites W4200161632 @default.
- W4368348057 doi "https://doi.org/10.1016/j.bdr.2023.100394" @default.
- W4368348057 hasPublicationYear "2023" @default.
- W4368348057 type Work @default.
- W4368348057 citedByCount "1" @default.
- W4368348057 countsByYear W43683480572023 @default.
- W4368348057 crossrefType "journal-article" @default.
- W4368348057 hasAuthorship W4368348057A5009976811 @default.
- W4368348057 hasAuthorship W4368348057A5030184407 @default.
- W4368348057 hasAuthorship W4368348057A5047604818 @default.
- W4368348057 hasAuthorship W4368348057A5057414572 @default.
- W4368348057 hasConcept C111919701 @default.
- W4368348057 hasConcept C118505674 @default.
- W4368348057 hasConcept C119857082 @default.
- W4368348057 hasConcept C124101348 @default.
- W4368348057 hasConcept C132525143 @default.
- W4368348057 hasConcept C13280743 @default.
- W4368348057 hasConcept C154945302 @default.
- W4368348057 hasConcept C185798385 @default.
- W4368348057 hasConcept C204321447 @default.
- W4368348057 hasConcept C205649164 @default.
- W4368348057 hasConcept C25343380 @default.
- W4368348057 hasConcept C2987255567 @default.
- W4368348057 hasConcept C41008148 @default.
- W4368348057 hasConcept C41608201 @default.
- W4368348057 hasConcept C80444323 @default.
- W4368348057 hasConceptScore W4368348057C111919701 @default.
- W4368348057 hasConceptScore W4368348057C118505674 @default.
- W4368348057 hasConceptScore W4368348057C119857082 @default.
- W4368348057 hasConceptScore W4368348057C124101348 @default.
- W4368348057 hasConceptScore W4368348057C132525143 @default.
- W4368348057 hasConceptScore W4368348057C13280743 @default.
- W4368348057 hasConceptScore W4368348057C154945302 @default.
- W4368348057 hasConceptScore W4368348057C185798385 @default.
- W4368348057 hasConceptScore W4368348057C204321447 @default.
- W4368348057 hasConceptScore W4368348057C205649164 @default.
- W4368348057 hasConceptScore W4368348057C25343380 @default.
- W4368348057 hasConceptScore W4368348057C2987255567 @default.
- W4368348057 hasConceptScore W4368348057C41008148 @default.
- W4368348057 hasConceptScore W4368348057C41608201 @default.
- W4368348057 hasConceptScore W4368348057C80444323 @default.
- W4368348057 hasFunder F4320321001 @default.
- W4368348057 hasLocation W43683480571 @default.
- W4368348057 hasOpenAccess W4368348057 @default.
- W4368348057 hasPrimaryLocation W43683480571 @default.
- W4368348057 hasRelatedWork W2793488029 @default.
- W4368348057 hasRelatedWork W2923818335 @default.
- W4368348057 hasRelatedWork W3094292840 @default.
- W4368348057 hasRelatedWork W3212418102 @default.
- W4368348057 hasRelatedWork W4221147115 @default.
- W4368348057 hasRelatedWork W4226361842 @default.
- W4368348057 hasRelatedWork W4285821569 @default.
- W4368348057 hasRelatedWork W4307647416 @default.
- W4368348057 hasRelatedWork W4318148049 @default.
- W4368348057 hasRelatedWork W4385574365 @default.
- W4368348057 hasVolume "33" @default.
- W4368348057 isParatext "false" @default.
- W4368348057 isRetracted "false" @default.
- W4368348057 workType "article" @default.