Scalable and interpretable rule-based link prediction for large heterogeneous knowledge graphs

TL;DR

This paper introduces SAFRAN, a scalable, interpretable rule-based framework that significantly improves link prediction in large biomedical knowledge graphs, achieving state-of-the-art results and faster inference.

Contribution

SAFRAN enhances the rule-based link prediction approach by scalable rule aggregation, enabling it to outperform existing methods on large-scale biomedical datasets.

Findings

SAFRAN achieves state-of-the-art results on FB15K-237 and OpenBioLink.

Inference speeds are increased by up to two orders of magnitude.

SAFRAN narrows the performance gap between rule-based and embedding-based methods.

Abstract

Neural embedding-based machine learning models have shown promise for predicting novel links in biomedical knowledge graphs. Unfortunately, their practical utility is diminished by their lack of interpretability. Recently, the fully interpretable, rule-based algorithm AnyBURL yielded highly competitive results on many general-purpose link prediction benchmarks. However, its applicability to large-scale prediction tasks on complex biomedical knowledge bases is limited by long inference times and difficulties with aggregating predictions made by multiple rules. We improve upon AnyBURL by introducing the SAFRAN rule application framework which aggregates rules through a scalable clustering algorithm. SAFRAN yields new state-of-the-art results for fully interpretable link prediction on the established general-purpose benchmark FB15K-237 and the large-scale biomedical benchmark OpenBioLink. Furthermore, it exceeds the results of multiple established embedding-based algorithms on FB15K-237 and narrows the gap between rule-based and embedding-based algorithms on OpenBioLink. We also show that SAFRAN increases inference speeds by up to two orders of magnitude.