Abstract
This paper addresses the problem of feature selection for Multi-class Support Vector Machines. Two models involving the \(\ell _{0}\) (the zero norm) and the \(\ell _{2}\)–\(\ell _{0}\) regularizations are considered for which two continuous approaches based on DC (Difference of Convex functions) programming and DCA (DC Algorithms) are investigated. The first is DC approximation via several sparse inducing functions and the second is an exact reformulation approach using penalty techniques. Twelve versions of DCA based algorithms are developed on which empirical computational experiments are fully performed. Numerical results on real-world datasets show the efficiency and the superiority of our methods versus one of the best standard algorithms on both feature selection and classification.
Similar content being viewed by others
Notes
The conjugate \(G^*\) of a convex function G is defined by \(G^*(Y):= \sup \limits _{X} \left\{ \langle X,Y \rangle - G(X) \right\} \).
References
Bradley, P. S., & Mangasarian, O. L. (1998). Feature selection via concave minimization and support vector machines. In J. Shavlik (Ed.), Machine learning proceedings of the fifteenth international conferences (ICML’98) (pp. 82–90). San Francisco: Morgan Kaufmann.
Cai, X., Nie, F., Huang, H., & Ding, C. (2011). Multi-class \(\ell _{2,1}\)-norm support vector machine. In Data mining (ICDM), 2011 IEEE 11th International Conference (pp. 91–100).
Candès, E. J., Wakin, M. B., & Boyd, S. P. (2008). Enhancing sparsity by reweighted \(\ell _{1}\) minimization. Journal of Fourier Analysis and Applications, 14, 877–905.
Chapelle, O. (2008). Multi-class feature selection with support vector machines. Technical report YR-2008-002.
Chen, Y. W., & Lin, C. J. (2006). Combining SVMs with various feature selection strategies. In I. Guyon, M. Nikravesh, S. Gunn, & L. A. Zadeh (Eds.), Feature extraction. Studies in Fuzziness and Soft Computing (Vol. 207, pp. 315–324). Berlin: Springer.
Chen, Y., Li, Y., Cheng, X-Q., & Guo, L. (2006). Survey and taxonomy of feature selection algorithms in intrusion detection system. In Proceedings of Inscrypt 2006, LNCS 4318 (pp. 153–167).
Chen, X., Zeng, X., & Alphen, D. V. (2006). Multi-class feature selection for texture classification. Pattern Recognition Letters, 27, 1685–1691.
Collobert, R., Sinz, F., Weston, J., & Bottou, L. (2006). Large scale transductive SVMs. Journal of Machine Learning Research, 7, 1687–1712.
Deng, S., Xu, Y., Li, L., Li, X., & He, Y. (2013). A feature-selection algorithm based on Support Vector Machine-multiclass for hyperspectral visible spectral analysis. Journal of Food Engineering, 119(1), 159–166.
Duan, K. B., Rajapakse, J. C., Wang, H., & Azuaje, F. (2005). Multiple SVM-RFE for genne selection in cancer classification with expression data. IEEE Transactions on Nanobioscience, 4, 228–234.
Fan, J., & Li, R. (2001). Variable selection via nonconcave penalized likelihood and its oracle properties. Journal of the American Statistical Association, 96, 1348–1360.
Gribonval, R., & Nielsen, M. (2003). Sparse representation in union of bases. IEEE Transactions on Information Theory, 49, 3320–73325.
Guyon, I., & Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of Machine Learning Research, 3, 1157–1182.
Guyon, I., Gunn, S., Nikravesh, M., & Zadeh, L. A. (2006). Feature extraction, foundations and applications. Berlin: Springer.
Hermes, L., & Buhmann, J. M. (2000). Feature selection for support vector machines. Proceedings of the 15th International Conference on Pattern Recognition, vol. 2 (pp. 712–715).
Hsu, C. W., & Lin, C. J. (2002). A comparison of methods for multiclass support vector machines. IEEE Transactions on Neural Networks, 13(2), 415–425.
Huang, J., Ma, S., & Zhang, C. H. (2008). Adaptive Lasso for sparse high-dimentional regression models. Statistica Sinica, 18, 1603–1618.
Huang, L., Zhang, H. H., Zeng, Z. B., & Bushel, P. R. (2013). Improved sparse multi-class SVM and its application for gene selection in cancer classification. Cancer Inform, 12, 143–153.
Hui, Z. (2006). The adaptive lasso and its oracle properties. Journal of the American Statistical Association, 101(476), 1418–1429.
Krause, N., & Singer, Y. (2004). Leveraging the margin more carefully. In Proceeding of ICML ’04 (pp. 63–71). NY, USA.
Le Thi, H. A. (2005). DC programming and DCA. Available on http://lita.sciences.univ-metz.fr/~lethi/DCA.html.
Le Thi, H. A. (2012). A new approximation for the \(\ell _{0}\) -norm. Research Report LITA EA 3097, University of Lorraine.
Le Thi, H. A., & Phan, D. N. (2016). DC programming and DCA for sparse fisher linear discriminant analysis. Neural Computing and Applications, doi:10.1007/s00521-016-2216-9.
Le Thi, H. A., Belghiti, T., & Pham Dinh, T. (2006). A new efficient algorithm based on DC programming and DCA for Clustering. Journal of Global Optimization, 37, 593–608.
Le Thi, H. A., Le Hoai, M., & Dinh, T. Pham. (2015). Feature Selection in machine learning: An exact penalty approach using a Difference of Convex function algorithm. Machine Learning, 101(1–3), 163–186.
Le Thi, H. A., Le Hoai, M., Nguyen, V. V., & Pham Dinh, T. (2008). A DC programming approach for feature selection in Support Vector Machines learning. Journal of Advances in Data Analysis and Classification, 2(3), 259–278.
Le Thi, H. A., Le Hoai, M., & Pham Dinh, T. (2007). Optimization based DC programming and DCA for hierarchical clustering. European Journal of Operational Research, 183, 1067–1085.
Le Thi, H. A., Huynh, V. N., & Pham Dinh, T. (2012). Exact penalty and error bounds in DC programming. Journal of Global Optimization, 52(3), 509–535.
Le Thi, H. A., Nguyen, V. V., & Ouchani, S. (2008). Gene selection for cancer classification using DCA. In C. Tang, C. X. Ling, X. Zhou, N. J. Cercone, & X. Li (Eds.), ADMA 2008. LNCS (LNAI) (Vol. 5139, pp. 62–72). Heidelberg: Springer.
Le Thi, H. A., & Pham Dinh, T. (2005). The DC (Difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems. Annals of Operations Research, 133, 23–46.
Le Thi, H. A., Pham Dinh, T., Le Hoai, M., & Vo, X. T. (2015). DC approximation approaches for sparse optimization. European Journal of Operational Research, 244(1), 26–46.
Le Thi, H. A., & Phan, D. N. (2016). DC programming and DCA for sparse optimal scoring problem. Neurocomputing, 186, 170–181.
Lee, Y., Kim, Y., Lee, S., & Koo, J. (2006). Structured multicategory support vector machines with analysis of variance decomposition. Biometrika, 93(3), 555–71.
Lee, Y., Lin, Y., & Wahba, G. (2004). Multicategory support vector machines, theory, and application to the classification of microarray data and satellite radiance data. Journal of the American Statistical Association, 99(465), 67–81.
Li, G. Z., Yang, J., Liu, G. P., & Xue, L. (2004). Feature selection for multi-class problems using support vector machines. In PRICAI 2004: Trends in artificial intelligence, lecture notes in computer science 3157 (pp. 292–300). Berlin: Springer.
Liu, D., Qian, H., Dai, G., & Zhang, Z. (2013). An iterative SVM approach to feature selection and classification in high-dimensional datasets. Pattern Recognition, 46(9), 2531–2537.
Liu, Y., & Shen, X. (2006). Multicategory \(\Psi \)-learning. Journal of the American Statistical Association, 101(474), 500–509.
Liu, Y., Shen, X., & Doss, H. (2005). Multicategory \(\psi \)-learning and Support Vector Machine: Computational tools. Journal of Computational and Graphical Statistics, 14, 219–236.
Liu, Y., Zhang, H. H., Park, C., & Ahn, J. (2007). Support vector machines with adaptive \(\ell _q\) penalty. Computational Statistics & Data Analysis, 51, 6380–6394.
Maldonado, S., Weber, R., & Basak, J. (2011). Simultaneous feature selection and classification using kernel-penalized support vector machines. Information Sciences, 181(1), 115–128.
Neumann, J., Schnörr, C., & Steidl, G. (2005). Combined SVM-based feature selection and classification. Machine Learning, 61(1–3), 129–150.
Ong, C. S., & Le Thi, H. A. (2013). Learning sparse classifiers with Difference of Convex functions algorithms. Optimization Methods and Software, 28, 4.
Peleg, D., & Meir, R. (2008). A bilinear formulation for vector sparsity optimization. Signal Processing, 8(2), 375–389.
Pham Dinh, T., & Le Thi, H. A. (2014). Recent advances on DC programming and DCA. In Transactions on computational intelligence XIII, Lecture Notes in Computer Science Vol. 8342 (pp. 1–37).
Pham Dinh, T., & Le Thi, H. A. (1997). Convex analysis approach to D.C. programming: Theory, algorithm and applications. Acta Mathematica Vietnamica, 22, 289–355.
Pham Dinh, T., & Le Thi, H. A. (1998). Optimization algorithms for solving the trust region subproblem. SIAMJ. Optimization, 2, 476–505.
Rakotomamonjy, A. (2003). Variable selection using SVM-based criteria. Journal of Machine Learning Research, 3, 1357–1370.
Ramona, M., Richard, G., & David, B. (2012). Multiclass feature selection with kernel gram-matrix-based criteria. IEEE Transactions on Neural Networks and Learning Systems, 23(10), 1611–1623.
Ronan, C., Fabian, S., Jason, W., & Lé, B. (2006). Trading convexity for scalability. In Proceedings of the 23rd international conference on machine learning ICML 2006 (pp. 201–208). Pittsburgh, Pennsylvania.
Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society, 46, 431–439.
Wang, H., Li, G., & Jiang, G. (2007). Robust regression shrinkage and consistent variable selection via the LAD-LASSO. Journal of Business & Economics Statistics, 25(3), 347–355.
Wang, L., & Shen, X. (2003). On \(\ell _1\)-norm multi-class support vector machine: Methodology and theory. Journal of the American Statistical Association, 102, 583–594.
Weston, J., & Watkins, C. (1999). Support vector machines for multi-class pattern recognition. In Proceedings-European symposium on artificial neural networks, ESANN 1999 (pp. 219–224). D-Facto public.
Weston, J., Elisseeff, A., & Schölkopf, B. (2003). Use of zero-norm with linear models and kernel methods. Journal of Machine Learning Research, 3, 1439–1461.
Wu, K., Lu, B., Uchiyama, M. & Isahara, H. (2007). A probabilistic approach to feature selection for multi-class text categorization. In D. Liu et al. (Eds.), ISNN 2007, Part I, LNCS 4491 (pp. 1310–1317).
Yeh, Y., Chung, Y., Lin, T., & Wang, Y. (2011). Group lasso regularized multiple kernel learning for heterogeneous feature selection. In The 2011 international joint conference on neural networks (IJCNN) (pp. 2570–2577).
Zhang, H. H., Liu, Y., Wu, Y., & Zhu, J. (2008). Variable selection for the multicategory SVM via adaptive sup-norm regularization. Journal of Statistics, 2, 149–167.
Zhou, Y., Jin, R. & Hoi, S. C. (2010). Exclusive lasso for multi-task feature selection. In AISTATS 9.
Zhou, X., & Tuck, D. P. (2007). MSVM-RFE: Extensions of SVM-RFE for multiclass gene selection on DNA microarray data. Bioinformatics, 23(9), 1106–1114.
Zou, H. (2006). The adaptive lasso and its oracle properties. Journal of the American Statistical Association, 101, 1418–71429.
Acknowledgments
This research is funded by Foundation for Science and Technology Development of Ton Duc Thang University (FOSTECT), website: http://fostect.tdt.edu.vn, under Grant FOSTECT.2015.BR.15. The authors would like to thank the referees and the guest editor for their valuable comments which helped to improve the manuscript.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Le Thi, H.A., Nguyen, M.C. DCA based algorithms for feature selection in multi-class support vector machine. Ann Oper Res 249, 273–300 (2017). https://doi.org/10.1007/s10479-016-2333-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10479-016-2333-y