Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph Completion

TL;DR

This paper introduces simple augmentation techniques for logical rule sets in neuro-symbolic knowledge graph completion, significantly improving model performance across multiple datasets.

Contribution

It proposes three straightforward rule augmentation methods—abductive transformation, inverse rule generation, and random walks—and demonstrates their effectiveness.

Findings

Up to 7.1 point MRR improvement

Up to 8.5 point Hits@1 improvement

Consistent performance gains across datasets

Abstract

High-quality and high-coverage rule sets are imperative to the success of Neuro-Symbolic Knowledge Graph Completion (NS-KGC) models, because they form the basis of all symbolic inferences. Recent literature builds neural models for generating rule sets, however, preliminary experiments show that they struggle with maintaining high coverage. In this work, we suggest three simple augmentations to existing rule sets: (1) transforming rules to their abductive forms, (2) generating equivalent rules that use inverse forms of constituent relations and (3) random walks that propose new rules. Finally, we prune potentially low quality rules. Experiments over four datasets and five ruleset-baseline settings suggest that these simple augmentations consistently improve results, and obtain up to 7.1 pt MRR and 8.5 pt Hits@1 gains over using rules without augmentations.