QuatE-D: A Distance-Based Quaternion Model for Knowledge Graph Embedding

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fazael-Ardakani, Hamideh-Sadat, Soltanian-Zadeh, Hamid
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909584512253952
author Fazael-Ardakani, Hamideh-Sadat
Soltanian-Zadeh, Hamid
author_facet Fazael-Ardakani, Hamideh-Sadat
Soltanian-Zadeh, Hamid
contents Knowledge graph embedding (KGE) methods aim to represent entities and relations in a continuous space while preserving their structural and semantic properties. Quaternion-based KGEs have demonstrated strong potential in capturing complex relational patterns. In this work, we propose QuatE-D, a novel quaternion-based model that employs a distance-based scoring function instead of traditional inner-product approaches. By leveraging Euclidean distance, QuatE-D enhances interpretability and provides a more flexible representation of relational structures. Experimental results demonstrate that QuatE-D achieves competitive performance while maintaining an efficient parameterization, particularly excelling in Mean Rank reduction. These findings highlight the effectiveness of distance-based scoring in quaternion embeddings, offering a promising direction for knowledge graph completion.
format Preprint
id arxiv_https___arxiv_org_abs_2504_13983
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle QuatE-D: A Distance-Based Quaternion Model for Knowledge Graph Embedding
Fazael-Ardakani, Hamideh-Sadat
Soltanian-Zadeh, Hamid
Machine Learning
Knowledge graph embedding (KGE) methods aim to represent entities and relations in a continuous space while preserving their structural and semantic properties. Quaternion-based KGEs have demonstrated strong potential in capturing complex relational patterns. In this work, we propose QuatE-D, a novel quaternion-based model that employs a distance-based scoring function instead of traditional inner-product approaches. By leveraging Euclidean distance, QuatE-D enhances interpretability and provides a more flexible representation of relational structures. Experimental results demonstrate that QuatE-D achieves competitive performance while maintaining an efficient parameterization, particularly excelling in Mean Rank reduction. These findings highlight the effectiveness of distance-based scoring in quaternion embeddings, offering a promising direction for knowledge graph completion.
title QuatE-D: A Distance-Based Quaternion Model for Knowledge Graph Embedding
topic Machine Learning
url https://arxiv.org/abs/2504.13983