Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry

We are concerned with the discovery of hierarchical relationships from large-scale unstructured similarity scores. For this purpose, we study different models of hyperbolic space and find that learning embeddings in the Lorentz model is substantially more efficient than in the Poincar\'e-ball m...

Full description

Saved in:
Bibliographic Details
Main Authors Nickel, Maximilian, Kiela, Douwe
Format Journal Article
LanguageEnglish
Published 09.06.2018
Subjects
Computer Science - Artificial Intelligence
Computer Science - Learning
Statistics - Machine Learning
Online AccessGet full text

Cover

More Information
Summary:We are concerned with the discovery of hierarchical relationships from large-scale unstructured similarity scores. For this purpose, we study different models of hyperbolic space and find that learning embeddings in the Lorentz model is substantially more efficient than in the Poincar\'e-ball model. We show that the proposed approach allows us to learn high-quality embeddings of large taxonomies which yield improvements over Poincar\'e embeddings, especially in low dimensions. Lastly, we apply our model to discover hierarchies in two real-world datasets: we show that an embedding in hyperbolic space can reveal important aspects of a company's organizational structure as well as reveal historical relationships between language families.
DOI:10.48550/arxiv.1806.03417