TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation

Proceedings of the 28th International Conference on Computational Linguistics, pages 1583–1593 Barcelona, Spain (Online), December 8-13, 2020 1583 TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation Chengjin Xu and Mojtaba Nayyeri and Fouad Alkhoury and Hamed Shariat Yazdi Smart Data Analytics Group, University of Bonn / Germany {xuc,nayyeri}@iai.uni-bonn.de s6foalkh@uni-bonn.de shariatyazdi@gmail.com Jens Lehmann University of Bonn / Germany Fraunhofer IAIS/ Germany jens.lehmann@iais.fraunhofer.de Abstract In the last few years, there has been a surge of interest in learning representations of entities and relations in knowledge graph (KG). However, the recent availability of temporal knowledge graphs (TKGs) that contain time information for each fact created the need for reasoning over time in such TKGs. In this regard, we present a new approach of TKG embedding, TeRo, which defines the temporal evolution of entity embedding as a rotation from the initial time to the current time in the complex vector space. Specially, for facts involving time intervals, each relation is represented as a pair of dual complex embeddings to handle the beginning and the end of the relation, respectively. We show our proposed model overcomes the limitations of the existing KG embedding models and TKG embedding models and has the ability of learning and inferring various relation patterns over time. Experimental results on four different TKGs show that TeRo significantly outperforms existing state-of-the-art models for link prediction. In addition, we analyze the effect of time granularity on link prediction over TKGs, which as far as we know has not been investigated in previous literature. 1 Introduction In recent years, a number of sizable Knowledge Graphs (KGs) have been constructed, including DBpe- dia (Auer et al., 2007), YAGO (Suchanek et al., 2007), Nell (Carlson et al., 2010) and Freebase (Bollacker et al., 2008). In these KGs, a fact is represented as a triple (s, r ,o), where s (subject) and o (object) are entities (nodes), and r (relation) is the relation (edge) between them. Several KG embedding (KGE) models are developed to perform learning and inference over these KGs (Bordes et al., 2013; Yang et al., 2014; Trouillon et al., 2016; Sun et al., 2019; Zhang et al., 2019). The most common learning task for these models is link prediction, which is to complete a fact with the missing entity. For instance, one can use a KGE model to perform an object query like (Barack Obama, visits, ?). In this case, there are several valid answers to this question, regardless of the time factor. Obviously, the inclusion of time information can make this query more specific, e.g., (Barack Obama, visits, ?, 2014-07-08). Some temporal KGs (TKGs) including ICEWS (Lautenschlager et al., 2015), GDELT (Leetaru and Schrodt, 2013), YAGO3 (Mahdisoltani et al., 2013) and Wikidata (Erxleben et al., 2014) store billions of time-aware facts as quadruples (s, r ,o, t) where t is the time annotation, e.g., (Barack Obama, vis- its, Ukraine, 2014-07-08). The availability of these TKGs that exhibits complex temporal dynamics in addition to its multi-relational nature has created the need for approaches …

Content truncated to 500 words