Ontology Alignment for Accurate Ontology Matching: A Survey

Abstract Edge computing, a distributed computing architecture within the knowledge-defined network (KDN), faces challenges due to significant disparities and data heterogeneity among its nodes, hindering their interaction. Ontology, solution Semantic Web, is well-suited for addressing matching ontologies effectively. However, ontology presents difficulties non-linear mathematical issues. To overcome these challenges, generative adversarial (GAN), an unsupervised learning method, has emerged as promising tool. GAN consists of two models with distinct objectives trained against eachother achieve optimal outcomes. This paper introduces SA-GAN, algorithm that combines simulation-based annealing enhance effectiveness. SA-GAN utilizes stagnation counter expedite convergence speed GAN. Through experiments conducted on renowned benchmark, demonstrates along other algorithms, can identify best alignments. Consequently, facilitates construction bridges in edge improving overall