English

Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition

Machine Learning 2020-10-29 v6 Artificial Intelligence Machine Learning

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.

Keywords

Cite

@article{arxiv.1911.07893,
  title  = {Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition},
  author = {Chengjin Xu and Mojtaba Nayyeri and Fouad Alkhoury and Hamed Shariat Yazdi and Jens Lehmann},
  journal= {arXiv preprint arXiv:1911.07893},
  year   = {2020}
}

Comments

This paper has been accepted by ISWC2020

R2 v1 2026-06-23T12:19:49.769Z