Toward value difference metric with attribute weighting

详细信息    查看全文

• 作者：Chaoqun Li ; Liangxiao Jiang ; Hongwei Li ; Jia Wu…
• 关键词：Distance metric learning ; Value difference metric ; Attribute weighting ; Mutual information
• 刊名：Knowledge and Information Systems
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：50
• 期：3
• 页码：795-825
• 全文大小：
• 刊物类别：Computer Science
• 刊物主题：Information Systems and Communication Service; IT in Business;
• 出版者：Springer London
• ISSN：0219-3116
• 卷排序：50

文摘

In distance metric learning, recent work has shown that value difference metric (VDM) with a strong attribute independence assumption outperforms other existing distance metrics. However, an open question is whether VDM with a less restrictive assumption can perform even better. Many approaches have been proposed to improve VDM by weakening the assumption. In this paper, we make a comprehensive survey on the existing improved approaches and then propose a new approach to improve VDM by attribute weighting. We name the proposed new distance function as attribute-weighted value difference metric (AWVDM). Moreover, we propose a modified attribute-weighted value difference metric (MAWVDM) by incorporating the learned attribute weights into the conditional probability estimates of AWVDM. AWVDM and MAWVDM significantly outperform VDM and inherit the computational simplicity of VDM simultaneously. Experimental results on a large number of UCI data sets validate the performance of AWVDM and MAWVDM.