Analysis of Gradient Descent Ontology Algorithm in Special Setting
Yun Gao, Wei Gao · International Journal of Applied Mathematics & Statistics/International journal of applied mathematics and statistics · 2014
Ontology as a useful tool has wide applications in various fields and raises widespread attention of scholars. And the ontology concept similarity calculation is an essential problem in these application algorithms. An effective method to get similarity between vertices on ontology is based on a function which maps ontology graph into a line and maps every vertex in graph into a real-value. The similarity is measured by the difference of their corresponding scores. In this paper, we focus on an ontology setting which uses truth function to label each pair of vertices and the ontology preferences are given randomly from some distributions on the set of possible undirected edge sets of an ontology graph. Based on the techniques of statistical learning theory, the learning rates for gradient descent ontology algorithm in such setting with general convex losses are obtained.