RGCN
An RGCN, or Relational Graph Convolution Network, is a an application of the GCN framework to modeling relational data, specifically to link prediction and entity classification tasks. See here for an in-depth explanation of RGCNs by DGL.
Papers with Code 아카이브
Knowledge Base Completion
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Knowledge base completion is the task which automatically infers missing facts by reasoning about the information already present in the knowledge base. A knowledge base is a collection of relational facts, often represented in the form of "subject", "relation", "object"-triples.
기법
관련 논문에서 소개한 기법입니다. 이 태스크에서의 평가 여부는 평가 결과에서 확인하세요.
ComplEx-N3
ComplEx model trained with a nuclear norm regularizer
Canonical Tensor Decomposition for Knowledge Base Completion
CP-N3
Canonical Tensor Decomposition, trained with N3 regularizer
Canonical Tensor Decomposition for Knowledge Base Completion
CP N3
CP with N3 Regularizer
Canonical Tensor Decomposition for Knowledge Base Completion
CP-N3-RP
CP with N3 Regularizer and Relation Prediction
ComplEx-N3-RP
ComplEx model trained with a nuclear norm regularizer; A relation prediction objective is added on top of the commonly used 1vsAll objective.
RESCAL-RP
RESCAL model trained with a relation prediction objective on top of the 1vsAll loss
TuckER-RP
TuckER model trained with a relation prediction objective on top of the 1vsAll loss
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.