Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition

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.

arXiv commentThis paper has been accepted by ISWC2020

References in corpus (3)

• RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space
• SimplE Embedding for Link Prediction in Knowledge Graphs
• Quaternion Knowledge Graph Embeddings

Cited by in corpus (7)

• Temporal Graph Networks for Deep Learning on Dynamic Graphs
• Representation Learning for Dynamic Graphs: A Survey
• Geometric Algebra based Embeddings for Static and Temporal Knowledge Graph Completion
• TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion
• TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation
• RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion
• TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion