Deep Learning for Ontology Reasoning

TL;DR

This paper introduces a deep learning approach to ontology reasoning using recursive neural networks, demonstrating competitive accuracy and significantly faster performance compared to traditional logic-based reasoners.

Contribution

It presents a novel deep learning model for ontology reasoning that outperforms existing logic-based systems in speed while maintaining high reasoning quality.

Findings

Achieved comparable or better reasoning accuracy than logic-based reasoners.

System was up to 100 times faster on benchmark datasets.

Validated effectiveness on large standard datasets.

Abstract

In this work, we present a novel approach to ontology reasoning that is based on deep learning rather than logic-based formal reasoning. To this end, we introduce a new model for statistical relational learning that is built upon deep recursive neural networks, and give experimental evidence that it can easily compete with, or even outperform, existing logic-based reasoners on the task of ontology reasoning. More precisely, we compared our implemented system with one of the best logic-based ontology reasoners at present, RDFox, on a number of large standard benchmark datasets, and found that our system attained high reasoning quality, while being up to two orders of magnitude faster.