RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5671–5681 June 6–11, 2021. ©2021 Association for Computational Linguistics 5671 RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion Youri Xu, Haihong E∗, Meina Song, wenyu song, Xiaodong Lv, wang haotian, yang jinrui School of Computer Science, Beijing University of Posts and Telecommunications, China {youri.xu,ehaihong,mnsong,swy9834,lvxiaodong,haotianwang,yangjinrui} @bupt.edu.cn Abstract Static knowledge graph (SKG) embedding (SKGE) has been studied intensively in the past years. Recently, temporal knowl- edge graph (TKG) embedding (TKGE) has emerged. In this paper, we propose a Recur- sive Temporal Fact Embedding (RTFE) frame- work to transplant SKGE models to TKGs and to enhance the performance of existing TKGE models for TKG completion. Different from previous work which ignores the continuity of states of TKG in time evolution, we treat the sequence of graphs as a Markov chain, which transitions from the previous state to the next state. RTFE takes the SKGE to ini- tialize the embeddings of TKG. Then it recur- sively tracks the state transition of TKG by passing updated parameters/features between timestamps. Specifically, at each timestamp, we approximate the state transition as the gra- dient update process. Since RTFE learns each timestamp recursively, it can naturally transit to future timestamps. Experiments on five TKG datasets show the effectiveness of RTFE. 1 Introduction Temporal knowledge graph (TKG) is an extension of static knowledge graphs (SKGs) which introduce the time dimension. In SKGs, facts are considered to be time-invariant (Sil and Cucerzan, 2014). In reality, facts are not always true. For example, the triple (Obama, President, United States) was true only from 2009 to 2016 and (Obama, married, Mitchell) since 1992. However, SKGs do not re- flect the change in facts over time. An example of TKG is shown in Figure 1. Besides, facts on so- cial networks, e-commerce platforms and trading platforms also change over time. Therefore, TKGs have the potential to improve the performance of question answering, search, recommendation and prediction based on KGs (Huang et al., 2020; Garg et al., 2020). ∗Corresponding author: Haihong E TKG can be expressed as a set of quadruples (subject, relation, object, timestamp). Different from SKGs which ignore the time attribute of facts, the facts of TKGs are distributed in timestamps, which can reflect the dynamic change of entities and relationships over time. Due to the limited coverage of KGs, TKGs are also incomplete. By completing TKG, missing and potential knowledge under specific timestamps can be found. In recent years, a lot of work (Bordes et al., 2013; Wang et al., 2014; Lin et al., 2015; Kazemi and Poole, 2018; Schlichtkrull et al., 2018; Sun et al., 2019; Zhang et al., 2020) has focused on KG com- pletion by methods of graph embedding. These efforts have yielded good results, but most of them focused on SKGs and required training in a large number of triples. However, the TKG under a certain timestamp is a sparse multi-relation graph (Esteban …

Content truncated to 500 words