Generating $SROI^-$ Ontologies via Knowledge Graph Query Embedding Learning

TL;DR

AConE is a novel, parameter-efficient query embedding method that explains knowledge graph queries using $SROI^-$ description logic axioms, improving accuracy and interpretability over existing models.

Contribution

AConE introduces a new approach to query embedding that models $SROI^-$ axioms as cones in complex space, enabling explanation and improved performance with fewer parameters.

Findings

AConE outperforms previous models on multiple datasets.

AConE achieves significant improvements on WN18RR.

The method provides interpretable axioms that enhance query answering.

Abstract

Query embedding approaches answer complex logical queries over incomplete knowledge graphs (KGs) by computing and operating on low-dimensional vector representations of entities, relations, and queries. However, current query embedding models heavily rely on excessively parameterized neural networks and cannot explain the knowledge learned from the graph. We propose a novel query embedding method, AConE, which explains the knowledge learned from the graph in the form of $SROI^-$ description logic axioms while being more parameter-efficient than most existing approaches. AConE associates queries to a $SROI^-$ description logic concept. Every $SROI^-$ concept is embedded as a cone in complex vector space, and each $SROI^-$ relation is embedded as a transformation that rotates and scales cones. We show theoretically that AConE can learn $SROI^-$ axioms, and defines an algebra whose operations correspond one to one to $SROI^-$ description logic concept constructs. Our empirical study on multiple query datasets shows that AConE achieves superior results over previous baselines with fewer parameters. Notably on the WN18RR dataset, AConE achieves significant improvement over baseline models. We provide comprehensive analyses showing that the capability to represent axioms positively impacts the results of query answering.