Hyperbolic Temporal Knowledge Graph Embeddings with Relational and Time Curvatures

TL;DR

This paper introduces Hercules, a novel hyperbolic embedding model that incorporates relation and time curvatures for improved temporal knowledge graph completion, demonstrating competitive performance on benchmark datasets.

Contribution

The paper proposes Hercules, a time-aware hyperbolic embedding model that extends AttH by modeling relation and time curvatures, advancing temporal knowledge graph embedding methods.

Findings

Hercules achieves state-of-the-art results on ICEWS datasets.

Increasing negative samples can improve AttH's performance without temporal modeling.

Time does not always enhance knowledge graph completion performance.

Abstract

Knowledge Graph (KG) completion has been excessively studied with a massive number of models proposed for the Link Prediction (LP) task. The main limitation of such models is their insensitivity to time. Indeed, the temporal aspect of stored facts is often ignored. To this end, more and more works consider time as a parameter to complete KGs. In this paper, we first demonstrate that, by simply increasing the number of negative samples, the recent AttH model can achieve competitive or even better performance than the state-of-the-art on Temporal KGs (TKGs), albeit its nontemporality. We further propose Hercules, a time-aware extension of AttH model, which defines the curvature of a Riemannian manifold as the product of both relation and time. Our experiments show that both Hercules and AttH achieve competitive or new state-of-the-art performances on ICEWS04 and ICEWS05-15 datasets. Therefore, one should raise awareness when learning TKGs representations to identify whether time truly boosts performances.