What relations are reliably embeddable in Euclidean space?
arXiv:1903.05347v37 citations
Originality Incremental advance
AI Analysis
This work addresses a foundational problem in knowledge graph representation, offering theoretical insights for researchers in machine learning and AI.
The paper tackles the problem of embedding relations as directed graphs into Euclidean space, characterizing which relations can be captured by three embedding types and providing bounds on dimensionality and precision.
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.