Generating $SROI^-$ Ontologies via Knowledge Graph Query Embedding Learning
Yunjie He, Daniel Hernandez, Mojtaba Nayyeri, Bo Xiong, Yuqicheng Zhu, Evgeny Kharlamov, Steffen Staab
TL;DR
This work addresses the challenge of explainable query answering over incomplete knowledge graphs by introducing AConE, a parameter-efficient method that learns $SROI^-$ description-logic axioms and expresses them as cone-based embeddings in the complex plane. By mapping KG entities and queries to a multicone algebra, AConE provides a one-to-one correspondence between logical constructs (e.g., existential, intersection, union, negation) and geometric operations (relational rotation, cone intersection, union of multicones, and negation). The approach yields competitive or superior query-answering performance with significantly fewer parameters, particularly on non-negation queries and the WN18RR-QA dataset, while offering clearer, axiom-backed explanations of learned knowledge. Limitations include biases from rotation commutativity, challenges with negation, and the non-closure of certain operations under the cone model; future work envisions richer ontologies (with concept names, RBoxes, and TBoxes) and broader applicability to real-world KG datasets. The results suggest that encoding logical patterns explicitly via the multicone framework can improve both interpretability and efficiency in graph-based query reasoning.
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.