Neural Reasoning for Robust Instance Retrieval in $\mathcal{SHOIQ}$

TL;DR

This paper introduces EBR, a neural reasoner for $\ ext{SHOIQ}$ that uses embeddings to approximate symbolic reasoning, offering robustness against data inconsistencies and errors in knowledge bases.

Contribution

The paper presents EBR, a neural reasoner that approximates symbolic reasoning in $\ ext{SHOIQ}$ using embeddings, improving robustness and scalability over traditional reasoners.

Findings

EBR is robust against missing data.

EBR outperforms traditional reasoners with erroneous data.

EBR effectively approximates instance retrieval in $\ ext{SHOIQ}$.

Abstract

Concept learning exploits background knowledge in the form of description logic axioms to learn explainable classification models from knowledge bases. Despite recent breakthroughs in neuro-symbolic concept learning, most approaches still cannot be deployed on real-world knowledge bases. This is due to their use of description logic reasoners, which are not robust against inconsistencies nor erroneous data. We address this challenge by presenting a novel neural reasoner dubbed EBR. Our reasoner relies on embeddings to approximate the results of a symbolic reasoner. We show that EBR solely requires retrieving instances for atomic concepts and existential restrictions to retrieve or approximate the set of instances of any concept in the description logic $\mathcal{SHOIQ}$. In our experiments, we compare EBR with state-of-the-art reasoners. Our results suggest that EBR is robust against missing and erroneous data in contrast to existing reasoners.