Improving rule mining via embedding-based link prediction
This work addresses the challenge of achieving explainable and generalizable link prediction for knowledge graph applications, though it is incremental as it builds on existing hybrid approaches.
The authors tackled the problem of combining rule mining and embedding-based methods for link prediction on knowledge graphs by proposing a method that enriches knowledge graphs with pre-trained embeddings before applying rule mining, resulting in the discovery of new valuable rules across seven benchmark datasets.
Rule mining on knowledge graphs allows for explainable link prediction. Contrarily, embedding-based methods for link prediction are well known for their generalization capabilities, but their predictions are not interpretable. Several approaches combining the two families have been proposed in recent years. The majority of the resulting hybrid approaches are usually trained within a unified learning framework, which often leads to convergence issues due to the complexity of the learning task. In this work, we propose a new way to combine the two families of approaches. Specifically, we enrich a given knowledge graph by means of its pre-trained entity and relation embeddings before applying rule mining systems on the enriched knowledge graph. To validate our approach, we conduct extensive experiments on seven benchmark datasets. An analysis of the results generated by our approach suggests that we discover new valuable rules on the enriched graphs. We provide an open source implementation of our approach as well as pretrained models and datasets at https://github.com/Jean-KOUAGOU/EnhancedRuleLearning