3D Rotation and Translation for Hyperbolic Knowledge Graph Embedding

TL;DR

This paper introduces 3H-TH, a hyperbolic space model that effectively captures complex relation patterns in knowledge graphs, improving accuracy and hierarchical representation in low-dimensional embeddings.

Contribution

The paper presents a novel 3D rotation and translation model in hyperbolic space that simultaneously captures multiple relation patterns, outperforming previous models in key aspects.

Findings

Outperforms existing models in accuracy and hierarchy recognition

Effective in low-dimensional embeddings

Maintains competitive performance in high-dimensional space

Abstract

The main objective of Knowledge Graph (KG) embeddings is to learn low-dimensional representations of entities and relations, enabling the prediction of missing facts. A significant challenge in achieving better KG embeddings lies in capturing relation patterns, including symmetry, antisymmetry, inversion, commutative composition, non-commutative composition, hierarchy, and multiplicity. This study introduces a novel model called 3H-TH (3D Rotation and Translation in Hyperbolic space) that captures these relation patterns simultaneously. In contrast, previous attempts have not achieved satisfactory performance across all the mentioned properties at the same time. The experimental results demonstrate that the new model outperforms existing state-of-the-art models in terms of accuracy, hierarchy property, and other relation patterns in low-dimensional space, meanwhile performing similarly in high-dimensional space.