SVDD Based Learning Algorithm with Progressive Transductive Support Vector Machines
XUE Zhen-Xia1,2, LIU San-Yang1, LIU Wan-Li1,3
1.Department of Applied Mathematics, Xidian University, Xi'an 7100712. Department of Mathematics, Henan Science and Technology University, Luoyang 4710033. Department of Mathematics, Luoyang Normal College, Luoyang 471022
Abstract In semi-supervised learning, progressive transductive support vector machine (PTSVM) has some drawbacks, such as few sample labeled in each iteration, low training speed, many backtrack learning steps, and unstable learning performance. Aiming at these problems, a fast progressive transductive support vector machines learning algorithm is proposed. It selects new unlabeled samples based on support vector domain description (SVDD) by using the information of support vectors. Using region labeling rule instead of pairwise labeling rule of PTSVM, the algorithm inherits progressive labeling and dynamic adjusting of the PTSVM. And meanwhile it increases the computational speed and keeps even improves the accuracy. Experimental results on synthetic and real datasets show the validity of the proposed algorithm.
[1] Vapnik V N. Statistical Learning Theory. New York, USA: Wiley, 1998 [2] Bennett K, Demiriz A. Semi-Supervised Support Vector Machines // Kearns M S, Solla S A, Cohn D A, eds. Advances in Neural Information Processing Systems. Cambridge, USA: MIT Press, 1999, 11: 368-374 [3] Chapelle O, Vapnik V, Weston J. Transductive Inference for Estimating Values of Functions // Kearns M S, Solla S A, Cohn D A, eds. Advances in Neural Information Processing Systems. Cambridge, USA: MIT Press, 1999, 11: 421-427 [4] Joachims T. Transductive Inference for Text Classification Using Support Vector Machines // Proc of the 16th International Conference on Machine Learning. Bled, Slovenia, 1999: 200-209 [5] Zhao Yinggang, Chen Qi, He Qinming. A Transductive Learning Algorithm Based on Support Vector Machine. Journal of Southern Yangtze University: Natural Science Edition, 2006, 5(4): 441-444 (in Chinese) (赵英刚,陈 奇,何钦铭.一种基于支持向量机的直推式学习算法.江南大学学报:自然科学版, 2006, 5(4): 441-444) [6] Chen Yisong, Wang Guoping, Dong Shihai. Learning with Progressive Transductive Support Vector Machines. Pattern Recognition Letters, 2003, 24(12): 1845-1855 [7] Shen Xinyu, Xu Hongli, Guan Tengfei. Image Classification Based on Transductive Support Vector Machines. Journal of Computer Applications, 2007, 27(6): 1463-1464,1467 (in Chinese) (沈新宇,许宏丽,官腾飞.基于直推式支持向量机的图像分类算法.计算机应用, 2007, 27(6): 1463-1464,1467) [8] Liao Dongping, Jiang Bin, Wei Xizhang, et al. Fast Learning Algorithm with Progressive Transductive Support Vector Machine. System Engineering and Electronics, 2007, 29(1): 87-91 (in Chinese) (廖东平,姜 斌,魏玺章,等.一种快速的渐进直推式支持向量机分类学习算法.系统工程与电子技术, 2007, 29(1): 87-91) [9] Tax D M J, Duin R P W. Support Vector Domain Description .Pattern Recognition Letters, 1999, 20(11/12/13): 1191-1199 [10] Ding Ailing, Liu Fang, Li Ying. Pre-Extracting Support Vector by Adaptive Projective Algorithm // Proc of the 6th International Conference on Signal Proceedings. Beijing, China, 2002, Ⅰ: 21-24 [11] Joachims T. SVMlight: Support Vector Machine[DB/OL].[2007-10-21]. http://www-ai.cs.uni-dortmund.de/SOFTWARE/SVM_LIGHT/svm_light_v3.html [12] Blake C, Merz C. UCI Repository of Machine Learning Datasets[DB/OL].[2007-5-21]. http://www.ics.uci.edu/~mlearn/MLRepository.html [13] Chapelle O, Zien A. Semi-Supervised Classification by Low Density Separation // Proc of the 10th International Workshop on Artificial Intelligence and Statistics. Bridge Town, Barbados, 2005: 57-64
2008, Vol. 21 
