RulE: Knowledge Graph Reasoning with Rule Embedding

TL;DR

RulE introduces a unified rule embedding framework for knowledge graph reasoning, combining logical rules and entity-relation embeddings to improve inference accuracy and robustness.

Contribution

The paper presents a novel method that jointly learns rule and entity embeddings, enabling soft logical inference and improved knowledge graph reasoning.

Findings

Outperforms existing embedding and rule-based methods on benchmarks.

Effectively integrates logical rules into embedding space.

Enhances KG reasoning with a simple yet effective approach.

Abstract

Knowledge graph (KG) reasoning is an important problem for knowledge graphs. In this paper, we propose a novel and principled framework called \textbf{RulE} (stands for {Rul}e {E}mbedding) to effectively leverage logical rules to enhance KG reasoning. Unlike knowledge graph embedding (KGE) methods, RulE learns rule embeddings from existing triplets and first-order {rules} by jointly representing \textbf{entities}, \textbf{relations} and \textbf{logical rules} in a unified embedding space. Based on the learned rule embeddings, a confidence score can be calculated for each rule, reflecting its consistency with the observed triplets. This allows us to perform logical rule inference in a soft way, thus alleviating the brittleness of logic. On the other hand, RulE injects prior logical rule information into the embedding space, enriching and regularizing the entity/relation embeddings. This makes KGE alone perform better too. RulE is conceptually simple and empirically effective. We conduct extensive experiments to verify each component of RulE. Results on multiple benchmarks reveal that our model outperforms the majority of existing embedding-based and rule-based approaches.