Temporal Knowledge Graph Completion Based on Time Series Gaussian Embedding

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 besides 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 significantly outperforms the state-of-the-art KGE models and the existing temporal KGE models on link prediction over four temporal KGs.

  • Published in:
    ISWC 2020: The Semantic Web – ISWC 2020 International Workshop on Software Clones (ISWC)
  • Type:
    Inproceedings
  • Authors:
    C. Xu, M. Nayyeri, F. Alkhoury, H. S. Yazdi, J. Lehmann
  • Year:
    2020

Citation information

C. Xu, M. Nayyeri, F. Alkhoury, H. S. Yazdi, J. Lehmann: Temporal Knowledge Graph Completion Based on Time Series Gaussian Embedding, International Workshop on Software Clones (ISWC), ISWC 2020: The Semantic Web – ISWC 2020, 2020, https://doi.org/10.1007/978-3-030-62419-4_37, Xu.etal.2020a,