Why Settle for Just One? Extending EL++ Ontology Embeddings with Many-to-Many Relationships

TL;DR

This paper enhances EL++ ontology embeddings by enabling the modeling of many-to-many relationships, significantly improving performance and expanding applicability to more expressive description logics.

Contribution

It introduces a simple, effective method to extend EL++ ontology embeddings to handle many-to-many relationships, overcoming previous limitations.

Findings

Substantial performance improvements over five baselines.

Effective extension for EL++ to handle complex relationships.

Potential to apply to more expressive description logics like SROIQ.

Abstract

Knowledge Graph (KG) embeddings provide a low-dimensional representation of entities and relations of a Knowledge Graph and are used successfully for various applications such as question answering and search, reasoning, inference, and missing link prediction. However, most of the existing KG embeddings only consider the network structure of the graph and ignore the semantics and the characteristics of the underlying ontology that provides crucial information about relationships between entities in the KG. Recent efforts in this direction involve learning embeddings for a Description Logic (logical underpinning for ontologies) named EL++. However, such methods consider all the relations defined in the ontology to be one-to-one which severely limits their performance and applications. We provide a simple and effective solution to overcome this shortcoming that allows such methods to consider many-to-many relationships while learning embedding representations. Experiments conducted using three different EL++ ontologies show substantial performance improvement over five baselines. Our proposed solution also paves the way for learning embedding representations for even more expressive description logics such as SROIQ.