Abstract
Semi-supervised multi-class classification focuses in machine learning and pattern recognition, and its most common approach is to decompose it into multiple binary classification problems. A novel class label presentation is proposed, which utilizes two-dimensional vector evenly distributed in circumference of unit circle to represent class label, so multi-class classification can be realized only once. Besides, local learning has the good performance in semi-supervised binary classification, and it is added to our algorithm to improve multi-class learning ability. The effectiveness of the algorithm is confirmed with experiments on six benchmark datasets compared to other related algorithms.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
O. Chapelle, Bernhard Scholkopf, A.zien, “Semi-supervised Learning,” MIT Press, 2006.
Z. Xiaojin, “Semi-supervised Learning Literature Survey,” Computer Sciences TR 1530, Univ. of Wisconsin, 2008.
G. Blanchard, G. Lee, C. Scott, “Semi-Supervised Novelty Detection,” Journal of Machine Learning Research, vol. 11, pp. 2973–3009, 2010.
M. Belkin, P. Niyogi, V. Sindhwani, “Manifold regularization: A geometric framework for learning from labeled and unlabeled examples,” Journal of Machine Learning Research, vol. 7, pp. 2399–2434, 2006.
T.Joachims, “Transductive learning via spectral graph partitioning,” Proc. 20th International Conference on Machine Learning, pp. 290–297, 2003.
X. Zh, Z. Ghaharmani, J. Lafferty, “Semi-supervised learning using gaussian fields and harmonic functions,” Proc. 20th International Conference on Machine Learning, pp. 912–919, 2003.
Dengyang Zhou, Olivier Bousquet, Thomas Navin Lal, Jason Weston, Bernhard Scholkopf, “Learning with local and global consistency,” Advances in Neural Information Processing Systems 16,MIT Press, pp. 321–328, 2003.
Mingrui Wu, Bernhard Scholkopf, “Transductive Classification via Local Learning Regularization,” Proc.of the 11th Int’1 Conf.on Artificial Intelligence and Statistics, pp. 624–631, 2007.
A. Torralba, K. P. Murphy, W. T. Freeman, “Sharing visual features for multiclass and multiview object detection”. PAMI, vol. 29, 854–869, 2007.
M. Belkin, I. Matveeva, P. Niyogi, “Tikhonov regularization and semi-supervised learning on large graphs,” 2004 Ieee International Conference on Acoustics, Speech, and Signal Processing, Vol Iii, Proceedings, pp. 1000–1003, 2004.
V. Vapnik, “The nature of statistical learning theory,” Springer-Verlag, Berlin, 1995.
L. Bottou and V. Vapnik, “Local Learning Algorithms,” Neural Computation, vol. 4, pp. 888–900, 1992.
V. Vapnik and L. Bottou, “Local Algorithms for Pattern Recognition and Dependencies Estimation,” Neural Computation, vol. 5, pp. 893–909, 1993.
Acknowledgments
This work was supported by the State Key Program of National Natural Science foundation of China (Grant No. 10831009) and National Natural Science foundation of China (Grant No. 70921061).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag London Limited
About this paper
Cite this paper
Jia, L. (2012). Semi-Supervised Multi-Class Classification Algorithm Based on Local Learning. In: Zhu, R., Ma, Y. (eds) Information Engineering and Applications. Lecture Notes in Electrical Engineering, vol 154. Springer, London. https://doi.org/10.1007/978-1-4471-2386-6_15
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2386-6_15
Publisher Name: Springer, London
Print ISBN: 978-1-4471-2385-9
Online ISBN: 978-1-4471-2386-6
eBook Packages: EngineeringEngineering (R0)