arXiv (Cornell University) · 2019 · 37 citations · 24 references
ComputingComputer ScienceKnowledge RepresentationMachine LearningNatural Language ProcessingGraph-based LearningKnowledge GraphsSemantic NetworksTemporal Data MiningTemporal Knowledge RepresentationUncertainty RepresentationEmbedding LearningGaussian DistributionsGraph EmbeddingsKnowledge Graph EmbeddingsKnowledge Graph RepresentationLink PredictionTemporal Knowledge GraphsTemporal Uncertainty
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.
24
Translating embeddings for modeling multi-relational data
Antoine Bordes, Nicolas Usunier, Jason Weston et al. · 2015 · 5.2K citations · Full text
Kurt Bollacker, Colin Evans, Praveen Paritosh et al. · 2008 · 5K citations
Fabian M. Suchanek, Gjergji Kasneci, Gerhard Weikum · 2007 · 3.9K citations · Full text