Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089424265> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3089424265 endingPage "840" @default.
- W3089424265 startingPage "833" @default.
- W3089424265 abstract "Knowledge graph completion is an important task that aims to predict the missing relational link between entities. Knowledge graph embedding methods perform this task by representing entities and relations as embedding vectors and modeling their interactions to compute the matching score of each triple. Previous work has usually treated each embedding as a whole and has modeled the interactions between these whole embeddings, potentially making the model excessively expensive or requiring specially designed interaction mechanisms. In this work, we propose the multi-partition embedding interaction (MEI) model with block term format to systematically address this problem. MEI divides each embedding into a multi-partition vector to efficiently restrict the interactions. Each local interaction is modeled with the Tucker tensor format and the full interaction is modeled with the block term tensor format, enabling MEI to control the trade-off between expressiveness and computational cost, learn the interaction mechanisms from data automatically, and achieve state-of-the-art performance on the link prediction task. In addition, we theoretically study the parameter efficiency problem and derive a simple empirically verified criterion for optimal parameter trade-off. We also apply the framework of MEI to provide a new generalized explanation for several specially designed interaction mechanisms in previous models." @default.
- W3089424265 created "2020-10-08" @default.
- W3089424265 creator A5000189848 @default.
- W3089424265 creator A5087434029 @default.
- W3089424265 date "2020-01-01" @default.
- W3089424265 modified "2023-09-23" @default.
- W3089424265 title "Multi-Partition Embedding Interaction with Block Term Format for Knowledge Graph Completion." @default.
- W3089424265 hasPublicationYear "2020" @default.
- W3089424265 type Work @default.
- W3089424265 sameAs 3089424265 @default.
- W3089424265 citedByCount "0" @default.
- W3089424265 crossrefType "proceedings-article" @default.
- W3089424265 hasAuthorship W3089424265A5000189848 @default.
- W3089424265 hasAuthorship W3089424265A5087434029 @default.
- W3089424265 hasConcept C114614502 @default.
- W3089424265 hasConcept C132525143 @default.
- W3089424265 hasConcept C154945302 @default.
- W3089424265 hasConcept C155281189 @default.
- W3089424265 hasConcept C202444582 @default.
- W3089424265 hasConcept C2524010 @default.
- W3089424265 hasConcept C2777210771 @default.
- W3089424265 hasConcept C33923547 @default.
- W3089424265 hasConcept C41008148 @default.
- W3089424265 hasConcept C41608201 @default.
- W3089424265 hasConcept C42812 @default.
- W3089424265 hasConcept C48903430 @default.
- W3089424265 hasConcept C75564084 @default.
- W3089424265 hasConcept C80444323 @default.
- W3089424265 hasConceptScore W3089424265C114614502 @default.
- W3089424265 hasConceptScore W3089424265C132525143 @default.
- W3089424265 hasConceptScore W3089424265C154945302 @default.
- W3089424265 hasConceptScore W3089424265C155281189 @default.
- W3089424265 hasConceptScore W3089424265C202444582 @default.
- W3089424265 hasConceptScore W3089424265C2524010 @default.
- W3089424265 hasConceptScore W3089424265C2777210771 @default.
- W3089424265 hasConceptScore W3089424265C33923547 @default.
- W3089424265 hasConceptScore W3089424265C41008148 @default.
- W3089424265 hasConceptScore W3089424265C41608201 @default.
- W3089424265 hasConceptScore W3089424265C42812 @default.
- W3089424265 hasConceptScore W3089424265C48903430 @default.
- W3089424265 hasConceptScore W3089424265C75564084 @default.
- W3089424265 hasConceptScore W3089424265C80444323 @default.
- W3089424265 hasLocation W30894242651 @default.
- W3089424265 hasOpenAccess W3089424265 @default.
- W3089424265 hasPrimaryLocation W30894242651 @default.
- W3089424265 hasRelatedWork W2098027503 @default.
- W3089424265 hasRelatedWork W2279754968 @default.
- W3089424265 hasRelatedWork W2888572441 @default.
- W3089424265 hasRelatedWork W2890445068 @default.
- W3089424265 hasRelatedWork W2901389313 @default.
- W3089424265 hasRelatedWork W2963121966 @default.
- W3089424265 hasRelatedWork W2963273260 @default.
- W3089424265 hasRelatedWork W2968101397 @default.
- W3089424265 hasRelatedWork W2997932512 @default.
- W3089424265 hasRelatedWork W2998900284 @default.
- W3089424265 hasRelatedWork W3023810035 @default.
- W3089424265 hasRelatedWork W3038274943 @default.
- W3089424265 hasRelatedWork W3039924378 @default.
- W3089424265 hasRelatedWork W3086346689 @default.
- W3089424265 hasRelatedWork W3094348748 @default.
- W3089424265 hasRelatedWork W3099128825 @default.
- W3089424265 hasRelatedWork W3126412650 @default.
- W3089424265 hasRelatedWork W3145277743 @default.
- W3089424265 hasRelatedWork W3160018782 @default.
- W3089424265 hasRelatedWork W3162693027 @default.
- W3089424265 isParatext "false" @default.
- W3089424265 isRetracted "false" @default.
- W3089424265 magId "3089424265" @default.
- W3089424265 workType "article" @default.