Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhu, Yihua, Shimodaira, Hidetoshi
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2305.13015
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916112923361280
author Zhu, Yihua
Shimodaira, Hidetoshi
author_facet Zhu, Yihua
Shimodaira, Hidetoshi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2305_13015
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle 3D Rotation and Translation for Hyperbolic Knowledge Graph Embedding
Zhu, Yihua
Shimodaira, Hidetoshi
Computation and Language
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.
title 3D Rotation and Translation for Hyperbolic Knowledge Graph Embedding
topic Computation and Language
url https://arxiv.org/abs/2305.13015