Neuro-Symbolic Integration for Reasoning and Learning on Knowledge Graphs

Abstract

The goal of this thesis is to address knowledge graph completion tasks using neuro-symbolic methods. Neuro-symbolic methods allow the joint use of symbolic information defined as rules in ontologies and knowledge graph embedding methods that represent the entities and the relations of the graph in the vector space. This approach has the potential to improve the resolution of knowledge graph completion tasks in terms of reliability, interpretability, data efficiency and robustness.