EM-RBR: a reinforced framework for knowledge graph completion from reasoning perspective

TL;DR

EM-RBR is a framework that combines rule-based reasoning with embedding models to improve knowledge graph completion by leveraging background logic rules for deeper relation inference.

Contribution

It introduces a novel framework that integrates rule-based reasoning with embedding models, enhancing link prediction accuracy in knowledge graphs.

Findings

EM-RBR outperforms previous models on FB15k, WN18, and FB15k-R datasets.

The framework achieves higher accuracy by utilizing background logic rules.

Performance improvements are especially notable on the new FB15k-R dataset.

Abstract

Knowledge graph completion aims to predict the new links in given entities among the knowledge graph (KG). Most mainstream embedding methods focus on fact triplets contained in the given KG, however, ignoring the rich background information provided by logic rules driven from knowledge base implicitly. To solve this problem, in this paper, we propose a general framework, named EM-RBR(embedding and rule-based reasoning), capable of combining the advantages of reasoning based on rules and the state-of-the-art models of embedding. EM-RBR aims to utilize relational background knowledge contained in rules to conduct multi-relation reasoning link prediction rather than superficial vector triangle linkage in embedding models. By this way, we can explore relation between two entities in deeper context to achieve higher accuracy. In experiments, we demonstrate that EM-RBR achieves better performance compared with previous models on FB15k, WN18 and our new dataset FB15k-R, especially the new dataset where our model perform futher better than those state-of-the-arts. We make the implementation of EM-RBR available at https://github.com/1173710224/link-prediction-with-rule-based-reasoning.