TransBox: EL++-closed Ontology Embedding

2024-10-18

arXiv.org

AI Summary

Existing OWL ontology embedding methods are limited to atomic concepts and roles, failing to model complex description logic (DL) axioms—such as those expressible in EL++—thus hindering ontology learning and ontology-mediated query answering. This paper introduces the first EL++-closed ontology embedding paradigm, enabling compositional vector representations for arbitrary complex concept expressions. Our approach jointly integrates translation-based modeling (TransE) with geometric box embeddings, and designs a unified optimization objective constrained by DL axioms alongside semantics-preserving composite operators. These operators explicitly capture one-to-many, many-to-one, and many-to-many relational patterns. Evaluated on multiple real-world ontology benchmarks, our method achieves state-of-the-art performance on complex axiom prediction tasks, significantly outperforming existing embedding models in both accuracy and expressiveness.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

OWL (Web Ontology Language) ontologies, which are able to represent both relational and type facts as standard knowledge graphs and complex domain knowledge in Description Logic (DL) axioms, are widely adopted in domains such as healthcare and bioinformatics. Inspired by the success of knowledge graph embeddings, embedding OWL ontologies has gained significant attention in recent years. Current methods primarily focus on learning embeddings for atomic concepts and roles, enabling the evaluation based on normalized axioms through specially designed score functions. However, they often neglect the embedding of complex concepts, making it difficult to infer with more intricate axioms. This limitation reduces their effectiveness in advanced reasoning tasks, such as Ontology Learning and ontology-mediated Query Answering. In this paper, we propose EL++-closed ontology embeddings which are able to represent any logical expressions in DL via composition. Furthermore, we develop TransBox, an effective EL++-closed ontology embedding method that can handle many-to-one, one-to-many and many-to-many relations. Our extensive experiments demonstrate that TransBox often achieves state-of-the-art performance across various real-world datasets for predicting complex axioms.

Problem

• Embedding OWL ontologies effectively
• Handling complex DL axioms
• Improving advanced reasoning tasks

Innovation

• EL++-closed ontology embeddings
• TransBox method
• handles complex DL axioms