Hyperbolic Temporal Knowledge Graph Embeddings with Relational and Time Curvatures
This work addresses the need for efficient temporal knowledge graph embeddings, but it is incremental as it builds on existing models and questions the necessity of time-awareness in such tasks.
The paper tackled the problem of temporal knowledge graph completion by showing that simply increasing negative samples in a non-temporal model (AttH) can match or exceed state-of-the-art temporal models, and proposed Hercules, a time-aware extension that achieves competitive or new SOTA performances on ICEWS04 and ICEWS05-15 datasets.
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.