Abstract
To deal with the cost sensitive and semi-supervised learning problems in Multi-view Dimensionality Reduction (MDR), we propose a Cost Sensitive Semi-Supervised Canonical Correlation Analysis \((\hbox {CS}^{3}\hbox {CCA}). \hbox {CS}^{3}\hbox {CCA}\) first uses the \(L_2\) norm approach to obtain the soft label for each unlabeled data, and then embed the misclassification cost into the framework of Canonical Correlation Analysis (CCA). Compared with existing CCA based methods, \(\hbox {CS}^{3}\hbox {CCA}\) has the following advantages: (1) It uses the \(L_2\) norm approach to infer the soft label for unlabeled data, which is computationally efficient and effective, especially for cost sensitive face recognition. (2) The objective function of \(\hbox {CS}^{3}\hbox {CCA}\) not only maximizes the soft cost sensitive within-class correlations and minimizes the soft cost sensitive between-class correlations in the inter-view, but also considers the class imbalance problem simultaneously. With the discriminant projections learned by \(\hbox {CS}^{3}\hbox {CCA}\), we employ it for cost sensitive face recognition. The experimental results on four well-known face data sets, including AR, Extended Yale B, PIE and ORL, demonstrate the effectiveness of \(\hbox {CS}^{3}\hbox {CCA}\).
Similar content being viewed by others
References
Sun SL (2013) A survey of multi-view machine learning. Neural Comput Appl 23(7):2031–2038
Xu C, Tao DC, Xu C (2013) A survey on multi-view learning. arXiv preprint, arXiv:1304.5634
Yu J, Tao DC, Rui Y, Cheng J (2013) Pairwise constraints based multiview features fusion for scene classification. Pattern Recognit 46(2):483–496
Kan M, Shan SG, Zhang HH, Lao SH, Chen XL (2012) Multi-view Discriminant Analysis. In: proceedings of the 12th European Conference on Computer Vision, Florence, pp 808–821
Diethe T, Hardoon DR, Shawe-Taylor J (2008) Multiview fisher discriminant analysis. In: Proceedings of NIPS workshop on learning from multiple source with applications to robotics, Edinburgh, pp 976–983
Hou C, Zhang C, Wu Y, Nie F (2010) Multiple view semi-supervised dimensionality reduction. Pattern Recognit 43(3):720–730
Cheng XH, Chen SC, Xue H, Zhou XD (2012) A unified dimensionality reduction framework for semi-paired and semi-supervised multi-view data. Pattern Recognit 45(5):2005–2018
Hotelling H (1936) Relation between two sets of variables. Biometrica 28(3/4):322–3377
Lai PL, Fyfe C (2010) Kernel and nonlinear canonical correlation analysis. Int J Neural Syst 10(5):365–377
Sun TK, Chen SC (2007) Locality preserving CCA with applications to data visualization and pose estimation. Image Vis Comput 25(5):531–543
Wang FS, Zhang DQ (2013) A new locality-preserving canonical correlation analysis Algorithm for multi-view dimensionality reduction. Neural Process Lett 37:135–146
Hardoon DR, Shawe-Taylor J (2011) Sparse canonical correlation analysis. Mach Learn 83(3):331–353
Chu DL, Liao LZ, Ng MK, Zhang X (2013) Sparse canonical correlation analysis: new formulation and algorithm. IEEE Trans Pattern Anal Mach Intell 35(12):3050–3065
Yuan YH, Sun QS, Ge HW (2014) Fractional-order embedding canonical correlation analysis and its applications to multi-view dimensionality reduction and recognition. Pattern Recognit 47:1411–1424
Sun TK, Chen SC, Yang JY, Shi PF (2008) A novel method of combined feature extraction for recognition. In: Proceedings of the IEEE international conference on data mining, Pisa, pp 1043–1048
Peng Y, Zhang DQ, Zhang JC (2010) A new canonical correlation analysis algorithm with local discrimination. Neural Process Lett 31:1–15
Sun SL, Xie XJ, Yang M (2015) Multiview uncorrelated discriminant analysis. IEEE Trans Cybern 99:1–13
Yang M, Sun SL (2014) Multi-view uncorrelated linear discriminant analysis with applications to handwritten digit recognition. International Joint Conference on Neural Networks. Beijing, pp 4175–4181
Sun L, Ji SW, Ye JP (2010) Canonical correlation analysis for multilabel classification: a least-squares formulation, extensions, and analysis. IEEE Trans Pattern Anal Mach Intell 33(1):194–200
He ZY, Chen C, Bu JJ, Li P, Cai D (2015) Multi-view based multi-label propagation for image annotation. Neurocomputing 168:853–860
Wang YQ, Li P, Yao C (2014) Hypergraph canonical correlation analysis for multi-label classification. Signal Process 105:258–267
Zhen Y, Gao Y, Yeung DY, Zha HY, Li XL (2016) Spectral multimodal hashing and its application to multimedia retrieval. IEEE Trans Cybern 46(1):27–38
Irie G, Arai H, Taniguchi Y (2015) Alternating co-quantization for cross-modal hashing. In: Proceedings of the IEEE international conference on computer vision. Santiago. pp 1886–1894
Shen XB, Sun QS (2014) A novel semi-supervised canonical correlation analysis and extensions for multi-view dimensionality reduction. J Vis Commun Image Represent 25:1894–1904
Wright J, Yang A, Sastry S, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210–227
Shi QF, Eriksson A, Shen CH (2011) Is face recognition really a compressive sensing problem?. In: Proceedings of the IEEE international conference on computer vision and pattern recognition. Colorado Springs. pp 553–560
Wan JW, Yang M, Gao Y, Chen YJ (2014) Pairwise costs in semisupervised discriminant analysis for face recognition. IEEE Trans Inf Forensics Secur 9(10):1569–1580
Lu JW, Tan YP (2010) Cost-sensitive subspace learning for face recognition. In: Proceedings of the IEEE international conference on computer vision and pattern recognition. San Francisco, pp 2661–2666
Lu JW, Zhou XZ, Tan YP, Shang YY, Zhou J (2012) Cost-sensitive semi-supervised discriminant analysis for face recognition. IEEE Trans Inf Forensics Secur 7(3):944–953
Miao LS, Liu MX, Zhang DQ (2012) Cost-sensitive feature selection with application in software defect prediction. In: Proceedings of the IEEE 21th international conference on pattern recognition. Tsukuba, pp 976–970
Wan JW, Yang M, Chen YJ (2015) Discriminative cost sensitive Laplacian score for face recognition. Neurocomputing 152:333–344
Martinez AM, Benavente R (1998) The AR face database. CVC Technical Report, 24
Georghiades AS, Belhumeur PN, Kriegman DJ (2001) From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Trans Pattern Anal Mach Intell 23(6):643–660
Turk M, Pentland A (1991) Eigenfaces for recognition. J Cognit Neurosci 3(1):71–86
Samaria F, Harter A (1994) Parameterisation of a stochastic model for human face identification. In: Proceedings of IEEE workshop applications computer vision. Sarasota, pp 138–142
Zhang Y, Zhou ZH (2010) Cost-sensitive face recognition. IEEE Trans Pattern Anal Mach Intell 32(10):1758–1769
Rencher AC (2002) Methods of multivariate, 2nd edn. Wiley, New York
Ting KM (2002) An instance-weighting method to induce cost-sensitive trees. IEEE Trans Knowl Data Eng 14(3):659–665
Liu XY, Zhou ZH (2006) The influence of class imbalance on cost-sensitive learning: an empirical study. In: Proceedings of the IEEE international conference on data mining. Hong Kong, pp 970–974
Ojala T, Pietikainen M, Harwood D (1996) A comparative study of texture measures with classification based on feature distributions. Pattern Recognit 29(1):51–59
Fernandez-Delgado M, Cernadas E, Barro S, Amorim D (2014) Do we need hundreds of classifiers to solve real world classification problems? J Mach Learn Res 15:3133–3281
Acknowledgments
Jianwu Wan—This work was supported in part by Key Project of National Natural Science Foundation of China under Grant 61432008, National Natural Science Foundation of China under Grants 61272222, 61272367, 61502058, 61572085, 61201096, Natural Science Foundation of Educational Committee of Jiangsu Province under Grant 15KJB520002, Foundation of Changzhou University under Grant ZMF13020060. The authors would like to thank the anonymous referees and the editors for their helpful comments and suggestions.
Author information
Authors and Affiliations
Corresponding author
Appendix 1
Appendix 1
In this section, we introduce to use SVD to solve the optimal problems of CCA, LPbSCCA and our \(\hbox {CS}^{3}\hbox {CCA}\), which are defined by Eqs. (1), (4) and (11), respectively. Note that, they can also be solved by computing a generalized eigenvalue decomposition problem, i.e., Eq. (2). As the form of their objective functions are similar, the only difference between them is the definitions of \(\tilde{M}_{xy}, \tilde{M}_{xx}\) and \(\tilde{M}_{yy}\), they can be unified written as follows:
Firstly, we define the Lagrange function of Eq. (12) as follows:
and get its partial derivatives:
By simple derivation, we can prove \(\lambda _1=\lambda _2\) and get:
In the following, we use the SVD to find the solution. Let \(H=\tilde{M}_{xx}^{-1/2}\tilde{M}_{xy}\tilde{M}_{yy}^{-1/2}, U=\tilde{M}_{xx}^{1/2}W_x, V=\tilde{M}_{yy}^{1/2}W_y\), Eq. (15) becomes:
Observing Eq. (16), we discover that it only needs to do SVD of the matrix \(H=UDV^T=\sum _{i=1}^d {\lambda _i u_iv_i^T}, U=[u_1,\ldots ,u_d], V=[v_1,\ldots ,v_d]\), and then the projection directions of \(W_x\) and \(W_y\) can be got respectively.
Rights and permissions
About this article
Cite this article
Wan, J., Wang, H. & Yang, M. Cost Sensitive Semi-Supervised Canonical Correlation Analysis for Multi-view Dimensionality Reduction. Neural Process Lett 45, 411–430 (2017). https://doi.org/10.1007/s11063-016-9532-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-016-9532-z