Domain-specific knowledge graph rule pattern mining based on generative adversarial networks

Abstract

Most existing knowledge graphs (KGs) in specific domains suffer from problems of insufficient structural knowledge mining, superficial constraint of rules, incomplete system of rule patterns and higher error rate in the process of automated rule generation. In this paper, we present an adversarial generative approach for rule mining based on generative adversarial networks (GANs). The method firstly extracted a rule set according to a specific rule pattern defined manually, the rule set is then used as the adversarial training dataset for the GAN, That is, the discriminator determines whether a rule is true or not by learning the pattern of the rule set, and the generator tricks the discriminator by forging rules and improves according to the feedback from the generator.Finally, a generator is obtained to generate new rules that conform to the rule pattern, and a discriminator is obtained to determine the confidence of the automatically constructed triples.