arXiv:1903.05347
What relations are reliably embeddable in Euclidean space?
원문 초록
We consider the problem of embedding a relation, represented as a directed graph, into Euclidean space. For three types of embeddings motivated by the recent literature on knowledge graphs, we obtain characterizations of which relations they are able to capture, as well as bounds on the minimal dimensionality and precision needed.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ReCDAP: Relation-Based Conditional Diffusion with Attention Pooling for Few-Shot Knowledge Graph Completion
Knowledge-augmented Pre-trained Language Models for Biomedical Relation Extraction
SMART: Relation-Aware Learning of Geometric Representations for Knowledge Graphs
Relation Extraction Across Entire Books to Reconstruct Community Networks: The AffilKG Datasets
GraphOracle: A Foundation Model for Knowledge Graph Reasoning
Enhancing Knowledge Graph Completion with Entity Neighborhood and Relation Context
토론
이 논문과 연결된 포럼 글이 아직 없습니다.