Knowledge graph representation learning model based on meta-information and logical rule enhancements

Existing knowledge graph representation learning (KGRL) models rely on explicit semantic information of triple structure and cannot fully mine the implicit semantic information in the knowledge graph (KG). Aiming to improve KGRL model performance and accuracy, making up for the disadvantages of existing research, we propose Melo (Meta-information and Logical rules), a novel KGRL model that leverages meta-information and logical rules of entities and relations. Melo first utilizes neighborhood structures of entities to obtain meta-information and ontological information, then it mines logical rules from the KG to infer high-confidence triples and expand the training samples. Finally, Melo realizes accurate and reliable representations of entities and relations with help of meta-, logical, and triple structure information. Experimental results on regular and sparse datasets show its enhanced performance when compared with baselines in terms of multiple evaluation metrics. Visualization methods are also utilized to demonstrate how meta-information, logical rules, and triple structure mutually and separately enhance training. (c) 2023 The Author(s). Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

Existing knowledge graph representation learning (KGRL) models rely on explicit semantic information of triple structure and cannot fully mine the implicit semantic information in the knowledge graph (KG). We propose a novel KGRL model, Melo, that leverages meta-information and logical rules of entities and relations to improve KGRL model performance and accuracy, making up for the disadvantages of existing research. Experimental results demonstrate that Melo enhances performance compared to baselines in terms of multiple evaluation metrics, and visualization methods show how meta-information, logical rules, and triple structure enhance training.