决定图框架下本体学习算法的稳定性分析

Stability Analysis of Ontology Learning Algorithm in Decision Graph Setting

传统的本体算法采用启发式的方法来计算语义相似度,而随着本体处理数据量的日益增大,越来越多的机器学习方法被用于本体函数的获取。稳定性是本体学习算法的必要条件,它要求在本体样本集做轻微改动的情况下不会对得到的最优本体函数产生本质的改变。文中研究了在本体样本集的依赖关系由图结构决定的框架下,本体学习算法的稳定性和对应的统计学特征。首先对传统的PO和LTO一致稳定性条件进行分析;其次在大样本情况下扩展一致稳定性条件,提出Pk和LkO一致稳定性并得到相关的理论结果;最后把替换本体样本和删除本体样本两种样本进行变换组合,提出在大本体样本前提下的组合一致稳定性概念,并利用统计学习理论的方法得到一般结果。此外,在各类稳定性条件下,对满足m-独立条件的本体学习算法的广义界进行了讨论。

Traditional ontology algorithms use heuristic tricks to calculate semantic similarity.With the increasing amount of data processed by ontology,more and more machine learning technologies are applied to get ontology functions.Stability is a necessary condition for ontology learning algorithms which requires that there is no substantial influence on the obtained optimal ontology function if the ontology sample set is slightly changed.This paper studies the stability and corresponding statistical characteristics of ontology learning algorithms in the setting that the dependency relation of ontology samples are characterized by a graph.Firstly,the traditional PO and LTO uniform stability conditions are analyzed.Then,the extended uniform stability conditions Pk and LkO for large samples are proposed,and related theoretical results are obtained.Finally,two sample transformations(replacement ontology samples and delete ontology samples)are combined to bring forward the concept of combined uniform stability in setting of large ontology samples,and general results are yielded by using statistical learning theory.In addition,under various stability conditions,the generalized bounds of ontology learning algorithms that satisfy the m-independent condition are discussed.