Towards Loosely-Coupling Knowledge Graph Embeddings and Ontology-based Reasoning
Zoi Kaoudi, Abelardo Carlos Martinez Lorenzo, Volker Markl

TL;DR
This paper proposes a loosely-coupled approach combining knowledge graph embeddings with domain-specific reasoning to improve link prediction accuracy, enabling integration of expert knowledge and surpassing existing hybrid methods.
Contribution
It introduces a flexible framework that integrates knowledge graph embeddings with reasoning, significantly enhancing prediction accuracy over traditional data-driven methods.
Findings
Up to 3x improvement in MRR accuracy over vanilla embeddings
Outperforms hybrid rule mining and reasoning solutions by up to 3.5x MRR
Demonstrates the effectiveness of combining domain knowledge with embeddings
Abstract
Knowledge graph completion (a.k.a.~link prediction), i.e.,~the task of inferring missing information from knowledge graphs, is a widely used task in many applications, such as product recommendation and question answering. The state-of-the-art approaches of knowledge graph embeddings and/or rule mining and reasoning are data-driven and, thus, solely based on the information the input knowledge graph contains. This leads to unsatisfactory prediction results which make such solutions inapplicable to crucial domains such as healthcare. To further enhance the accuracy of knowledge graph completion we propose to loosely-couple the data-driven power of knowledge graph embeddings with domain-specific reasoning stemming from experts or entailment regimes (e.g., OWL2). In this way, we not only enhance the prediction accuracy with domain knowledge that may not be included in the input knowledge…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Graph Neural Networks · Topic Modeling · Data Quality and Management
