Laplacian smooth twin support vector machine for semi-supervised classification

Laplacian smooth twin support vector machine for semi-supervised classification
复制标题

用于半监督分类的拉普拉斯平滑双支持向量机

DOI:
10.1007/s13042-013-0183-3
复制
发表时间:
2013-07
影响因子:
5.6
通讯作者:
Hong Ning
Hong Ning
中科院分区:
计算机科学3区
文献类型:
--
作者:
Chen Wei-Jie;Shao Yuan-Hai;Hong Ning

文献摘要

参考文献

被引文献

相似文献

拉普拉斯双支持向量机(Lap-TSVM)是目前最先进的非平行平面半监督分类器。它试图利用嵌入在未标记数据中的几何信息来提高其泛化能力。然而,由于Lap-TSVM需要通过矩阵“逆”运算来求解两个二次规划问题,因此在训练过程中可能会承受较大的负担。为了提高Lap-TSVM的性能,本文提出了一种新的Lap-TSVM公式,称为Lap-STSVM。首先,我们将Lap-TSVM的原始约束qp问题转化为无约束最小化问题,而不是在对偶空间中求解两个qp问题。然后,引入了一种光滑技术使这些ump二次可微。最后,设计了一种快速的Newton-Armijo算法来求解Lap-STSVM中的不确定性问题。在人工和真实数据集上的实验评估表明了所提出方法的优点。
Laplacian twin support vector machine (Lap-TSVM) is a state-of-the-art nonparallel-planes semi-supervised classifier. It tries to exploit the geometrical information embedded in unlabeled data to boost its generalization ability. However, Lap-TSVM may endure heavy burden in training procedure since it needs to solve two quadratic programming problems (QPPs) with the matrix “inversion” operation. In order to enhance the performance of Lap-TSVM, this paper presents a new formulation of Lap-TSVM, termed as Lap-STSVM. Rather than solving two QPPs in dual space, firstly, we convert the primal constrained QPPs of Lap-TSVM into unconstrained minimization problems (UMPs). Afterwards, a smooth technique is introduced to make these UMPs twice differentiable. At last, a fast Newton–Armijo algorithm is designed to solve the UMPs in Lap-STSVM. Experimental evaluation on both artificial and real-world datasets demonstrate the benefits of the proposed approach.
DOI: 10.1016/j.patcog.2011.03.031
发表时间: 2011-10
期刊: Pattern Recognit.
影响因子: --
作者:
X. Peng
通讯作者: X. Peng
DOI: 10.1007/s00521-012-1108-x
发表时间: 2012-08
影响因子: 6
作者:
Zhixia Yang;Y. Shao;Xiang-Sun Zhang
通讯作者: Zhixia Yang;Y. Shao;Xiang-Sun Zhang
DOI: 10.5555/1953048.2021038
发表时间: 2009-09
期刊: J. Mach. Learn. Res.
影响因子: --
作者:
S. Melacci;M. Belkin
通讯作者: S. Melacci;M. Belkin
用于分类的最小二乘递归投影双支持向量机
DOI: 10.1016/j.patcog.2011.11.028
发表时间: 2012-06-01
影响因子: 8
作者:
Shao, Yuan-Hai;Deng, Nai-Yang;Yang, Zhi-Min
通讯作者: Yang, Zhi-Min
DOI: 10.1109/tnnls.2012.2214488
发表时间: 2012-10
影响因子: 10.4
作者:
Rodrigo G. F. Soares;Huanhuan Chen;X. Yao
通讯作者: Rodrigo G. F. Soares;Huanhuan Chen;X. Yao