Learning a Mahalanobis distance metric for data clustering and classification
Learning a Mahalanobis distance metric for data clustering and classification
复制标题
学习用于数据聚类和分类的马氏距离度量
DOI：
10.1016/j.patcog.2008.05.018
复制
发表时间：
2008-12-01
影响因子：
8
通讯作者：
Zhang, Changshui
中科院分区：
文献类型：
--
作者：
Xiang, Shiming;Nie, Feiping;Zhang, Changshui
距离度量是许多机器学习算法中的关键问题。本文考虑了从必须链接和不能链接形式的成对约束中学习的一般问题。作为一种辅助信息，必须链接表示两个数据点对必须属于同一类，而不能链接表示两个数据点必须属于两个不同类。给定必须链接和不能链接的信息，我们的目标是学习马氏距离度量。在这个度量下，我们希望必须链接中的点对的距离尽可能小，而不能链接中的点对的距离尽可能大。该任务被表述为一个约束优化问题，其中可以有效且高效地获得全局最优值。最后，本文给出了在数据聚类、交互式自然图像分割和人脸姿态估计中的一些应用。实验结果说明了我们算法的有效性。 (C) 2008 Elsevier Ltd. 保留所有权利。
Distance metric is a key issue in many machine learning algorithms. This paper considers a general problem of learning from pairwise constraints in the form of must-links and cannot-links. As one kind of side information, a must-link indicates the pair of the two data points must be in a same class, while a cannot-link indicates that the two data points must be in two different classes. Given must-link and cannot-link information, our goal is to learn a Mahalanobis distance metric. Under this metric, we hope the distances of point pairs in must-links are as small as possible and those of point pairs in cannot-links are as large as possible. This task is formulated as a constrained optimization problem, in which the global optimum can be obtained effectively and efficiently. Finally, some applications in data clustering, interactive natural image segmentation and face pose estimation are given in this paper. Experimental results illustrate the effectiveness of our algorithm. (C) 2008 Elsevier Ltd. All rights reserved.