EARR: Using rules to enhance the embedding of knowledge graph

Abstract

Knowledge graphs have been receiving increasing attention from researchers. However, most of these graphs are incomplete, leading to the rise of knowledge graph completion as a prominent task. The goal of knowledge graph completion is to find missing relations in a knowledge graph. Knowledge graph embedding represents the entities and relations in a low-dimensional embedding space, simplifying operations and allowing for integration with knowledge graph completion tasks. Several popular embedding models, such as TransE, TransH, TransR, TuckER, RotatE, and others have achieved impressive results on knowledge graph completion tasks. However, most of these methods do not incorporate background knowledge that could enhance the quality of knowledge embedding. Logic rules are adaptable and scalable, which can enrich background knowledge, and separating the attributes of entities can improve the relevance of relations and facilitate the accuracy of logic rule extraction. Thus, we propose a novel method, named Entity–Attribute–Relation–Rule (EARR), which separates attributes from entities and uses logic rules to extend the dataset, improving the accuracy of knowledge graph completion tasks. We define a total of six rules in this paper, including Rule 1–3, Rule 5, and Rule 6 for entities, and Rule 4 for entities and attributes. We evaluate our method based on the task of link prediction through two kinds of experiments. In the basic experiment, we compare our method with three benchmark models, namely, TransE, TransH, and TransR. In the experiment with different size datasets, FB24K and CoDEx, we evaluate our method on different size datasets with different models, including TransE, TuckER, and RotatE. The experimental results indicate that EARR can improve the quality of knowledge graph embedding.