UniKER: A Unified Framework for Combining Embedding and Definite Horn Rule Reasoning for Knowledge Graph Inference

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9753–9771 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 9753 UniKER: A Unified Framework for Combining Embedding and Definite Horn Rule Reasoning for Knowledge Graph Inference Kewei Cheng1, Ziqing Yang2, Ming Zhang2, and Yizhou Sun1 1Department of Computer Science, University of California, Los Angeles, Los Angeles, CA 2Department of Computer Science, School of EECS, Peking University, Beijing, China viviancheng@cs.ucla.edu, yangziqing@pku.edu.cn mzhang_cs@pku.edu.cn, yzsun@cs.ucla.edu Abstract Knowledge graph inference has been studied extensively due to its wide applications. has been addressed by two lines of research,It i.e., the more traditional logical rule reasoning and the more recent knowledge graph embed- ding (KGE). Several attempts have been made to combine KGE and logical rules for bet- ter knowledge graph inference. Unfortunately, they either simply treat logical rules as addi- tional constraints into KGE loss or use prob- abilistic models to approximate the exact log- ical inference (i.e., MAX-SAT). Even worse, both approaches need to sample ground rules to tackle the scalability issue, as the total num- ber of ground rules is intractable in practice, making them less effective in handling logical rules. In this paper, we propose a novel frame- work UniKER to address these challenges by restricting logical rules to be definite Horn rules, which can fully exploit the knowledge in logical rules and enable the mutual enhance- ment of logical rule-based reasoning and KGE in an extremely efficient way. Extensive exper- iments have demonstrated that our approach is superior to existing state-of-the-art algorithms in terms of both efficiency and effectiveness. 1 Introduction Knowledge Graphs (KGs) have grown rapidly recently which provide remarkably valuable re- sources for many real-world applications (Auer et al., 2007; Bollacker et al., 2008; Suchanek et al., 2007). KG reasoning, which aims at inferring miss- ing knowledge through the existing facts, is the key to the success of many downstream tasks and have received wide attention. Knowledge Graph Embedding (KGE) methods currently hold the state-of-the-art in KG reason- ing (Bordes et al., 2013; Wang et al., 2014; Yang et al., 2014; Sun et al., 2019). They aim to capture the similarity of entities via exploring rich structure information in KGs to predict unseen triples. De- spite the excellent performance of KGE methods, the ignorance of possible high-order constraints specified by logical rules limits their application in more complex reasoning tasks. In Fig. 1, for example, we can infer Stilwell lives in USA based on KGE, due to her similarity with Miller in terms of embeddings, as both can be reached via the same relation transformation (i.e. isMarriedTo) from the same entity (Edison). But without the capability of leveraging logical rules, we cannot infer Stilwell and Miller speak English. An alternative solution is to infer missing facts via logical rules, which have been extensively explored by traditional logical rule-based meth- ods (Richardson and Domingos, 2006; De Raedt and Kersting, 2008). As shown in Fig. 1, two entities (e.g., Miller and English) that are not directly connected in …

Content truncated to 500 words