RelDiff

2000년 도입 · 논문 1편에서 사용

RelDiff generates entity-relation-entity embeddings in a single embedding space. RelDiff adopts two fundamental vector algebraic operators to transform entity and relation embeddings from knowledge graphs into entity-relation-entity embeddings. In particular, RelDiff can encode finer-grained information about the relations than is captured when separate embeddings are learned for the entities and the relations.

출처: RelDiff: Enriching Knowledge Graph Relation Representations for Sensitivity Classification

소개 논문: RelDiff: Enriching Knowledge Graph Relation Representations for Sensitivity Classification