Temporal Knowledge Graph Completion with Time-sensitive Relations in Hypercomplex Space

TL;DR

This paper introduces a quaternion-based approach for temporal knowledge graph completion that effectively models complex time-sensitive relations, achieving state-of-the-art results by capturing diverse temporal patterns.

Contribution

It proposes a novel quaternion representation focusing on time-sensitive relations, enhancing the modeling of temporal variability in knowledge graphs.

Findings

Achieves state-of-the-art performance on public datasets.

Effectively models symmetric, asymmetric, inverse, and evolutionary relations.

Demonstrates the superiority of hypercomplex space representations in TKGC.

Abstract

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.