Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition

TL;DR

This paper introduces ATiSE, a novel temporal knowledge graph embedding model that uses additive time series decomposition and Gaussian distributions to incorporate temporal information and uncertainty, achieving state-of-the-art link prediction results.

Contribution

The paper presents ATiSE, a new temporal KG embedding approach that models temporal dynamics and uncertainty using additive time series and Gaussian distributions.

Findings

ATiSE achieves state-of-the-art link prediction performance.

Incorporates temporal uncertainty into entity/relation representations.

Utilizes additive time series decomposition for temporal modeling.

Abstract

Knowledge Graph (KG) embedding has attracted more attention in recent years. Most KG embedding models learn from time-unaware triples. However, the inclusion of temporal information beside triples would further improve the performance of a KGE model. In this regard, we propose ATiSE, a temporal KG embedding model which incorporates time information into entity/relation representations by using Additive Time Series decomposition. Moreover, considering the temporal uncertainty during the evolution of entity/relation representations over time, we map the representations of temporal KGs into the space of multi-dimensional Gaussian distributions. The mean of each entity/relation embedding at a time step shows the current expected position, whereas its covariance (which is temporally stationary) represents its temporal uncertainty. Experimental results show that ATiSE chieves the state-of-the-art on link prediction over four temporal KGs.