Please wait a minute...
浙江大学学报(工学版)
J4  2012, Vol. 46 Issue (6): 987-994    DOI: 10.3785/j.issn.1008-973X.2012.06.005
计算机技术     
局部敏感判别直推学习机
潘俊1,2, 孔繁胜1, 王瑞琴2
1. 浙江大学 计算机科学与技术学院,浙江 杭州 310027;2. 温州大学 物理与电子信息工程学院,浙江 温州 325035
Locality sensitive discriminant transductive learning
PAN Jun1,2, KONG Fan-sheng1, WANG Rui-qin2
1. College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China;
2. College of Physics and Electronic Information Engineering, Wenzhou University, Wenzhou 325035, China
 全文: PDF  HTML
摘要：

为了充分挖掘样本内在的几何结构和蕴含的判别信息来指导样本数据分类,提出一种局部敏感的判别直推学习方法.该方法将局部敏感辨析（LSDA）的基本原理引入到直推学习中,在直推学习的正则化框架中同时引入有助于分类的样本局部结构信息和判别信息,在判别信息指导下构建了类内图和类间图来刻画类内紧性和类间散性,从而在每个局部邻域中进一步最大化类间样本的间隔.同时,用数学的形式给出了目标函数的解析表达,在几个典型数据集上的实验结果表明,相较传统的基于图的半监督学习算法,该方法能取得更高的分类效果.
Abstract:

A novel approach called locality sensitive discriminant transductive learning (LSD-TL) was developed in order to utilize the underlying geometric structure and the discriminant information to full extent in the process of data classification. Inspired by the basic theories of the locality sensitive discriminant analysis (LSDA), LSD-TL directly incorporates the discriminative information as well as the local geometry of the data space into the regularization framework of transductive learning. LSD-TL constructs the within-class graph and the between-class graph under the guidance of the discriminative information, so that the margins between the data of different classes in each local manifold are maximized. In addition, the analytical solution for the problem was obtained. Experimental results on real world datasets demonstrated that compared with several traditional graph-based semi-supervised algorithms, the new approach improved the classification accuracy.
出版日期: 2012-07-24
:  TP 181  
基金资助:

浙江省自然科学基金资助项目（Q12F020047）.
通讯作者: 孔繁胜,男,教授.     E-mail: kfs@cs.zju.edu.cn
作者简介: 潘俊（1978—）,男,博士生,从事机器学习、语义挖掘研究.E-mail: panjun@wzu.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

潘俊, 孔繁胜, 王瑞琴. 局部敏感判别直推学习机[J]. J4, 2012, 46(6): 987-994.

PAN Jun, KONG Fan-sheng, WANG Rui-qin. Locality sensitive discriminant transductive learning. J4, 2012, 46(6): 987-994.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2012.06.005    或    http://www.zjujournals.com/eng/CN/Y2012/V46/I6/987

［1］ ZHU Xiaojin. Semisupervised learning literature survey［R］. Wisconsin, USA: Department of Computer Sciences, University of Wisconsin, 2008.
［2］ YAN Shuicheng, XUDong, ZHANG Benyu, et al. Graph embedding and extensions: a general framework for dimensionality reduction［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(1): 40-51.
［3］ QIU Xipeng, WU Lide. Face recognition by stepwise nonparametric margin maximum criterion［C］∥ Proceedings of the 10th International Conference on Computer Vision. Beijing: IEEE Computer Society ,2005: 1567-1572.
［4］ CAI Deng, HE Xiaofei, ZHOU Kun, et al. Locality sensitive discriminant analysis［C］∥International Joint Conference on Artificial Intelligence. Hyderabad: Morgan Kaufmann Publishers, 2007: 708-713.
［5］ 魏莱,王守觉.基于流形距离的半监督判别分析［J］.软件学报, 2010, 21(10): 2445-2453.
WEI Lai, WANG Shoujue. Semisupervised discriminant analysis based on manifold distance ［J］. Journal of Software, 2010, 21(10): 2445-2453.
［6］ 杨剑,王珏,钟宁.流形上的Laplacian半监督回归［J］.计算机研究与发展, 2007, 44(7): 1121-1127.
YANG Jian, WANG Jue, ZHONG Ning. Laplacian semisupervised regression on a manifold ［J］. Journal of Computer Research and Development, 2007, 44(7): 1121-1127.
［7］ 朱凤梅,张道强.张量图像上的半监督降维算法［J］.模式识别与人工智能,2009,22(4): 574-580.
ZHU Fengmei, ZHANG Daoqiang. Semisupervised dimensionality reduction algorithm of tensor image ［J］. Pattern Recognition and Artificial Intelligence, 2009, 22(4): 574-580.
［8］ BELKIN M, NIYOGI P, SINDHWANI V. Manifold Regularization: A geometric framework for learning from labeled and unlabeled examples.［J］. Journal of Machine Learning Research, 2006, 7(11): 2399-2434.
［9］ 皋军,王士同,邓赵红.基于全局和局部保持的半监督支持向量机［J］.电子学报, 2010, 38(7): 1626-1633.
GAO Jun, WANG Shihong, DENG Zhaohong. Global and local preserving based semisupervised support vector machine［J］. Acta Electronica Sinica, 2010, 38(7): 1626-1633.
［10］ ZHOU D, BOUSQUEN O, LAL T N, et al. Learning with local and global consistency［C］∥ Advances in Neural Information Processing Systems. Cambridge: MIT, 2004: 321-328.
［11］ 孔祥南,黎铭,姜远,等.一种针对弱标记的直推式多标记分类方法［J］.计算机研究与发展,2010, 47(8): 1392-1399.
KONG Xiangnan, LI Ming, JIANG Yuan, et al. A transductive multilabel classification method for weak labeling［J］. Journal of Computer Research and Development, 2010, 47(8): 1392-1399.
［12］ 李明,杨艳屏,占惠融.基于局部聚类与图方法的半监督学习方法［J］.自动化学报, 2010, 36(12): 1655-1660.
LI Ming, YANG Yanping, ZHAN Huirong. Semisupervised learning based on graph and local quick shift［J］. Acta Automatica Sinica, 2010, 36(12): 1655-1660.
［13］ XUE Hui, CHEN Songcan, YANG Qiang, Discriminatively regularized leastsquares classification ［J］.Pattern Recognition, 2009,42(1): 93-104.
［14］ CHUNG F R K. Spectral graph theory［M］. Fresno, USA: American Mathematical Society, 1997.
［15］ CRAMMER K, SINGER Y. On the algorithmic implementation of multiclass kernelbased vector machines ［J］ The Journal of Machine Learning Research, 2002, 2(3): 265-292.
［16］ SCHLKOPH B, HERBRICH R, SMOLA A J, et al. A generalized representer theorem［C］∥ Proceedings of the 14th Annual Conference on Computational Learning Theory. Amsterdam: Springer Press,2001: 416-426.
［17］ BLAKE C, MERZ J. UCI repository of machine learning databases［DB/OL］. ［2010-06-26］. http:∥archive.ics.uci.edu/ml.
［18］ SAMARIA F, HARTER A. Parameterization of a Stochastic Model for Human Face Identification［C］∥ Proc of the 2nd IEEE Workshop on Applications of Computer Vision. Sarasota, USA: IEEE, 1994: 138-142.
［19］ VANPANIK V. Statistical learning theory［M］. New York: Wiley,1998.
[1] 林亦宁, 韦巍, 戴渊明. 半监督Hough Forest跟踪算法[J]. J4, 2013, 47(6): 977-983.
[2] 李侃,黄文雄,黄忠华. 基于支持向量机的多传感器探测目标分类方法[J]. J4, 2013, 47(1): 15-22.
[3] 王洪波, 赵光宙, 齐冬莲, 卢达. 一类支持向量机的快速增量学习方法[J]. J4, 2012, 46(7): 1327-1332.
[4] 艾解清, 高济, 彭艳斌, 郑志军. 基于直推式支持向量机的协商决策模型[J]. J4, 2012, 46(6): 967-973.
[5] 金卓军, 钱徽, 朱淼良. 基于倾向性分析的轨迹评测技术[J]. J4, 2011, 45(10): 1732-1737.
[6] 顾弘, 赵光宙. 广义局部图像距离函数下的图像分类与识别[J]. J4, 2011, 45(4): 596-601.
[7] 罗建宏,陈德钊. 兼顾正确率和差异性的自适应集成算法及应用[J]. J4, 2011, 45(3): 557-562.
[8] 商秀芹, 卢建刚, 孙优贤. 基于遗传规划的铁矿烧结终点2级预测模型[J]. J4, 2010, 44(7): 1266-1269.
[9] 徐磊, 赵光宙, 顾弘. 成对耦合分类器的多球体预处理方法[J]. J4, 2010, 44(2): 237-242.