Paper:
Error-Correcting Semi-Supervised Pattern Recognition with Mode Filter on Graphs
Weiwei Du* and Kiichi Urahama**
*Department of Information Science, Kyoto Institute of Technology, Matsugasaki, Sakyo-ku, Kyoto 606-8585, Japan
**Department of Communication Design Science, Kyushu University, 4-9-1 Shiobaru, Minamiku, Fukuoka 815-8540, Japan
A robust semi-supervisedmethod using the mode filter has been presented for learning with partially-labeled training data including label errors. The mode filter has been originally developed for smoothing images contaminated with impulsive noises. However it needs nonlinear optimization which is usually solved with iterative methods. In this paper, we propose a direct solution method with full search of solution spaces. This direct method outperforms the iterative algorithm in classification rates and computational speeds. Additional iterations of the mode filter raise up the classification rates. We extend the mode filter by introducing weights based on the isolation degree of data, and show the effectiveness of this extension.
- [1] C. E. Brodley and M. A. Friedl., “Identifying and eliminating mislabeled training instances,” Proc. NCAI, pp. 799-805, 1996.
- [2] P. Hartono and S. Hashimoto, “Learning from imperfect data,” Applied Soft Comput., pp. 353-363, 2007.
- [3] U. Rebbapragada and C. E. Brodley, “Class noise mitigation through instance weighting,” Proc. ECML, pp. 708-715, 2007.
- [4] N. D. Lawrence and B. Scholkopf, “Estimating a kernel fisher discriminant in the presence of label noise,” Proc. ICML, pp. 306-313, 2001.
- [5] M. R. Amini and P. Gallinari, “Semi-supervised learning with an imperfect supervisor,” Know. Inf. Syst., pp. 385-413, 2005.
- [6] Y. Li, L. F. A.Wessels, D. de Ridder, andM. J. T. Reinders, “Classification in the presence of class noise using a probabilistic kernel fisher method,” Patt. Recog., pp. 3349-3357, 2007.
- [7] M. Belkin, I. Matveeva, and P. Niyogi, “Regularization and semisupervised learning on large graphs,” Proc.COLT, pp. 624-638, 2004.
- [8] J. van deWeijer and R. van den Boomgaard, “Local mode filtering,” Proc. CVPR, pp. 428-433, 2001.
- [9] W. Du and K. Urahama, “Error-correcting semi-supervised learning with mode-filter on graphs,” Proc. WS-LAVD in ICCV, 2009.
- [10] X. Zhu, Z. Ghahramani, and J. D. Lafferty, “Semi-supervised learning using Gaussian fields and harmonic functions,” Proc. ICML, pp. 912-919, 2003.
- [11] http://archive.ics.uci.edu/ml/datasets.html
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.