Two improved attribute weighting schemes for value difference metric
Two improved attribute weighting schemes for value difference metric
复制标题
两种改进的价值差异度量属性加权方案
DOI:
10.1007/s10115-018-1229-3
复制
发表时间:
2018-06
影响因子:
2.7
通讯作者:
Li Chaoqun
中科院分区:
文献类型:
--
作者:
Jiang Liangxiao;Li Chaoqun
Due to its simplicity, efficiency and efficacy, value difference metric (VDM) has continued to perform well against more sophisticated newcomers and thus has remained of great interest to the distance metric learning community. Of numerous approaches to improving VDM by weakening its attribute independence assumption, attribute weighting has received less attention (only two attribute weighting schemes) but demonstrated remarkable class probability estimation performance. Among two existing attribute weighting schemes, one is non-symmetric and the other is symmetric. In this paper, we propose two simple improvements for setting attribute weights for use with VDM. One is the non-symmetric Kullback–Leibler divergence weighted value difference metric (KLD-VDM) and the other is the symmetric gain ratio weighted value difference metric (GR-VDM). We performed extensive evaluations on a large number of datasets and found that KLD-VDM and GR-VDM significantly outperform two existing attribute weighting schemes in terms of the negative conditional log likelihood and root relative squared error, yet at the same time maintain the computational simplicity and robustness that characterize VDM.
登录
查看更多内容
影响因子:
5.1
作者:
Li, Chaoqun;Jiang, Liangxiao;Li, Hongwei
通讯作者:
Li, Hongwei
DOI:
--
发表时间:
2014
期刊:
Journal of management science
影响因子:
--
作者:
อนิรุธ สืบสิงห์
通讯作者:
อนิรุธ สืบสิงห์
DOI:
10.1109/cvpr.2000.855863
发表时间:
2000
期刊:
Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)
影响因子:
--
作者:
C. Domeniconi;D. Gunopulos;Jing Peng
通讯作者:
C. Domeniconi;D. Gunopulos;Jing Peng
影响因子:
8.5
作者:
Qiu, chen;Jiang, Liangxiao;Li, Chaoqun
通讯作者:
Li, Chaoqun
DOI:
--
发表时间:
1992-10
期刊:
--
影响因子:
--
作者:
J. R. Quinlan
通讯作者:
J. R. Quinlan