一种基于约束的中垂面相似度准则

A Mid-Perpendicular Hyperplane Similarity Criterion Based on Pairwise Constraints

在数据挖掘和机器学习的基于距离的各种技术中,例如基于距离的聚类和基于距离的分类,如何度量数据间的相似性已经成为一项基础任务.对于某一具体问题,采用合适的相似性度量,会使问题得到更有效的解决.越来越多的研究表明,通过对成对约束(正约束和负约束)的充分利用,从而得到与问题相匹配的相似性度量,能够大幅度地提升算法性能.目前基于约束的相似性度量研究主要是基于约束的距离度量学习,通过对约束信息的利用,学习一个距离度量矩阵,然后再进行分类或者聚类.通过对成对约束尤其是负约束的挖掘,提出一种基于成对约束的相似性度量准则,然后将此准则应用于聚类和分类任务中,分别提出聚类和分类算法,最后在大量标准数据集上将这些算法的性能与目前流行的算法进行实验比较,并据此得出了一些经验性的启示.

Measuring the similarity between data objects is one of the primary tasks for distance-based techniques in data mining and machine learning, e. g. , distance-based clustering or classification. For a certain problem, using proper similarity measurement will make it easier to be solved. Recently, more and more researches have shown that pairwise constraints can help to obtain a good similarity measurement for certain problem with significantly improved performances. Most existing works on similarity measurement with pairwise constraints are on distance metric learning, which use pairwise constraints to learn a distance matrix for subsequent classification or clustering. In this paper, inspired by the hyperplance used in nearest neighbor and support vector machine classifiers, we propose a new similarity measurement criterion called mid-perpendicular hyperplane similarity （MPHS） which can effectively learn from pairwise constraints, especially cannot- Then we apply it for clustering and classification tasks. Finally, we validate the elf proposed method by comparing it with several state-of-the-art algorithms th experiments on a number of benchmark datasets. link constraints. ectiveness of our rough extensive experiments on a number of benchmark datasets.