Lattice-preserving $\mathcal{ALC}$ ontology embeddings with saturation

TL;DR

This paper introduces a novel lattice-preserving embedding method for $ ext{ALC}$ ontologies that leverages Category Theory, outperforming existing methods in knowledge base completion tasks and effectively handling ontologies without individuals.

Contribution

It presents a new semantic-preserving embedding approach for $ ext{ALC}$ ontologies using lattice structures and saturation, addressing limitations of prior methods that require individuals.

Findings

Outperforms state-of-the-art in knowledge base completion

Handles ontologies without individuals effectively

Increases information content with saturation procedures

Abstract

Generating vector representations (embeddings) of OWL ontologies is a growing task due to its applications in predicting missing facts and knowledge-enhanced learning in fields such as bioinformatics. The underlying semantics of OWL ontologies are expressed using Description Logics (DLs). Initial approaches to generate embeddings relied on constructing a graph out of ontologies, neglecting the semantics of the logic therein. Recent semantic-preserving embedding methods often target lightweight DL languages like $\mathcal{EL}^{++}$, ignoring more expressive information in ontologies. Although some approaches aim to embed more descriptive DLs like $\mathcal{ALC}$, those methods require the existence of individuals, while many real-world ontologies are devoid of them. We propose an ontology embedding method for the $\mathcal{ALC}$ DL language that considers the lattice structure of concept descriptions. We use connections between DL and Category Theory to materialize the lattice structure and embed it using an order-preserving embedding method. We show that our method outperforms state-of-the-art methods in several knowledge base completion tasks. Furthermore, we incoporate saturation procedures that increase the information within the constructed lattices. We make our code and data available at \url{https://github.com/bio-ontology-research-group/catE}.