Ontology Similarity Measure and Ontology Mapping via Learning Optimization Similarity Function

Ontology similarity calculation and ontology mapping are important research topics in information retrieval. By learning optimization similarity function, we propose the new algorithm for ontology similarity measure and ontology mapping. The stability of ontology algorithms is studied by adopting a strategy which adjusts the sample set by deleting one or two element from it. Relationship between uniform loss stability and uniform score stability is investigated. A sufficient condition for uniform score stability is given. The result of our work shows that if for any (v,v') ∈ V × V, a kernel function K((v,v'), (v,v')) has a limited upper bound, then the ontology algorithm which minimizes the regularization empirical l-error will have good uniform score stability. Also, two experiments results show that the proposed algorithm has high accuracy and efficiency for similarity calculation and ontology mapping. Index Terms—Ontology, similarity calculation, ontology mapping.