UniKER: A Unified Framework for Combining Embedding and Horn Rules for Knowledge Graph Inference

user-5f8411ab4c775e9685ff56d3(2020)

引用 4|浏览23
暂无评分
摘要
Knowledge graph inference has been studied extensively due to its wide applications in different domains. There are two main directions in solving the inference problem, i.e., logical rule reasoning and knowledge graph embedding (KGE). Logical rule-based approaches have shown their effectiveness due to the power of symbolic reasoning but suffer from low coverage, noise-sensitive, and scalability issues. KGE methods have demonstrated their good scalability when coping with large scale real-world KGs but fail to capture high-order dependency between entities and relations. Several attempts have been made to combine KG embedding and logical rules for better knowledge graph inference. Unfortunately, these approaches employ sampling strategies to randomly select only a small portion of ground rules or hidden triples, thus only partially leverage the power of logical rules in reasoning. In this paper, we propose a novel framework UniKER to address this challenge by restricting logical rules to be Horn rules, which can fully exploit the knowledge in logical rules and enable the mutual enhancement of logical rule-based reasoning and KGE in an extremely efficient way. Extensive experiments have demonstrated that our approach is superior to existing state-of-the-art algorithms in terms of both efficiency and effectiveness. ACM Reference Format: Kewei Cheng, Ziqing Yang, Ming Zhang, and Yizhou Sun. 2020. UniKER: A Unified Framework for Combining Embedding and Horn Rules for Knowledge Graph Inference. In Proceedings of The Second International Workshop on Deep Learning on Graphs: Methods and Applications (DLG-KDD’20). , 9 pages. https://doi.org/10.1145/nnnnnnn.nnnnnnn
更多
查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要