Salvato in:
Dettagli Bibliografici
Autori principali: Cai, Li, Mao, Xin, Wang, Zhihong, Zhao, Shangqing, Zhou, Yuhao, Wu, Changxu, Lan, Man
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2403.02355
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916146168463360
author Cai, Li
Mao, Xin
Wang, Zhihong
Zhao, Shangqing
Zhou, Yuhao
Wu, Changxu
Lan, Man
author_facet Cai, Li
Mao, Xin
Wang, Zhihong
Zhao, Shangqing
Zhou, Yuhao
Wu, Changxu
Lan, Man
contents Temporal knowledge graph completion (TKGC) aims to fill in missing facts within a given temporal knowledge graph at a specific time. Existing methods, operating in real or complex spaces, have demonstrated promising performance in this task. This paper advances beyond conventional approaches by introducing more expressive quaternion representations for TKGC within hypercomplex space. Unlike existing quaternion-based methods, our study focuses on capturing time-sensitive relations rather than time-aware entities. Specifically, we model time-sensitive relations through time-aware rotation and periodic time translation, effectively capturing complex temporal variability. Furthermore, we theoretically demonstrate our method's capability to model symmetric, asymmetric, inverse, compositional, and evolutionary relation patterns. Comprehensive experiments on public datasets validate that our proposed approach achieves state-of-the-art performance in the field of TKGC.
format Preprint
id arxiv_https___arxiv_org_abs_2403_02355
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Temporal Knowledge Graph Completion with Time-sensitive Relations in Hypercomplex Space
Cai, Li
Mao, Xin
Wang, Zhihong
Zhao, Shangqing
Zhou, Yuhao
Wu, Changxu
Lan, Man
Machine Learning
Artificial Intelligence
Temporal knowledge graph completion (TKGC) aims to fill in missing facts within a given temporal knowledge graph at a specific time. Existing methods, operating in real or complex spaces, have demonstrated promising performance in this task. This paper advances beyond conventional approaches by introducing more expressive quaternion representations for TKGC within hypercomplex space. Unlike existing quaternion-based methods, our study focuses on capturing time-sensitive relations rather than time-aware entities. Specifically, we model time-sensitive relations through time-aware rotation and periodic time translation, effectively capturing complex temporal variability. Furthermore, we theoretically demonstrate our method's capability to model symmetric, asymmetric, inverse, compositional, and evolutionary relation patterns. Comprehensive experiments on public datasets validate that our proposed approach achieves state-of-the-art performance in the field of TKGC.
title Temporal Knowledge Graph Completion with Time-sensitive Relations in Hypercomplex Space
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2403.02355