LogicENN: A Neural Based Knowledge Graphs Embedding Model With Logical Rules

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 6; pp. 7050 - 7062
• Main Authors: Nayyeri, Mojtaba, Xu, Chengjin, Alam, Mirza Mohtashim, Lehmann, Jens, Yazdi, Hamed Shariat
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.06.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Analytical models; Cognitive tasks; Computational modeling; Embedding; Encoding; Equivalence; Graphs; Grounding; Knowledge; Knowledge graph; Knowledge representation; link prediction; logical rule injection; Machine learning; neural networks; Optimization; Predictive models; relational reasoning; representation learning; Task analysis; Vector spaces
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2021.3121646

Knowledge graph embedding models have gained significant attention in AI research. The aim of knowledge graph embedding is to embed the graphs into a vector space in which the structure of the graph is preserved. Recent works have shown that the inclusion of background knowledge, such as logical rules, can improve the performance of embeddings in downstream machine learning tasks. However, so far, most existing models do not allow the inclusion of rules. We address the challenge of including rules and present a new neural based embedding model (LogicENN). We prove that LogicENN can learn every ground truth of encoded rules in a knowledge graph. To the best of our knowledge, this has not been proved so far for the neural based family of embedding models. Moreover, we derive formulae for the inclusion of various rules, including (anti-)symmetric, inverse, irreflexive and transitive, implication, composition, equivalence and negation. Our formulation allows to avoid grounding for implication and equivalence relations. Our experiments show that LogicENN outperforms the existing models in link prediction.