Temporal Knowledge Graph Embedding Model based on Additive Time Series Decomposition
This work addresses the need for improved temporal modeling in knowledge graphs, which is incremental as it builds on existing embedding methods by adding time-aware components.
The paper tackles the problem of incorporating temporal information into knowledge graph embeddings by proposing ATiSE, a model that uses additive time series decomposition and maps representations into Gaussian distributions to handle temporal uncertainty, achieving state-of-the-art results on link prediction across four temporal knowledge graphs.
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.