Abstract
Semi-supervised dimensionality reduction has attracted an increasing amount of attention in this big-data era. Many algorithms have been developed with a small number of pairwise constraints to achieve performances comparable to those of fully su pervised methods. However, one challenging problem with semi-supervised approaches is the appropriate choice of the constraint set, including the cardinality and the composition of the constraint set which, to a large extent, affects the performance of the resulting algorithm. In this work, we address the problem by incorporating ensemble subspaces and active learning into dimensionality reduction and propose a new global and local scatter based semi-supervised dimensionality reduction method with active constraints selection. Unlike traditional methods that select the supervised information in one subspace, we pick up pairwise constraints in ensemble subspaces, where a novel active learning algorithm is designed with both exploration and filtering to generate informative pairwise constraints. The automatic constraint selection approach proposed in this paper can be generalized to be used with all constraint-based semi-supervised learning algorithms. Comparative experiments are conducted on four face database and the results validate the effectiveness of the proposed method.
Similar content being viewed by others
References
Averbuch A, Rabin N, Schclar A et al (2012) Dimensionality reduction for detection of moving vehicles. Pattern Anal Appl 15(1):19–27
Borges HB, Nievola JC (2012) Comparing the dimensionality reduction methods in gene expression databases. Expert Syst Appl 39(12):10780–10795
Turk M, Pentland A (1991) Eigenfaces for recognition. J Cogn Neurosci 3(1):71–86
He X, Niyogi (2004) Locality preserving projections. In: Proceedings of advances in neural information processing systems, pp 153–160
Martinez AM, Kak AC (2001) PCA versus LDA. IEEE Trans Pattern Anal Mach Intell 23(2):228–233
Li H, Jiang T, Zhang K (2006) Efficient and robust feature extraction by maximum margin criterion. IEEE Trans Neural Netw 17(1):157–165
An S, Liu W, Venkatesh S (2008) Exploiting side information in locality preserving projection. In: International conference on computer vision and pattern recognition, pp 1–8
Hou C, Nie F, Wu Y (2011) Semi-supervised dimensionality reduction via harmonic functions. Modeling decision for artificial intelligence. Springer, Berlin Heidelberg, pp 91–102
Nie F, Xu D, Tsang IWH et al (2010) Flexible manifold embedding: a framework for semi-supervised and unsupervised dimension reduction. IEEE Trans Image Process 19(7):1921–1932
Zhao M, Zhan C, Wu Z et al (2015) Semi-supervised image classification based on local and global regression. IEEE Signal Process Lett 22(10):1666–1670
Gao Q, Huang Y, Gao X et al (2015) A novel semi-supervised learning for face recognition. Neurocomputing 152:69–76
Xiang S, Nie F, Zhang C (2008) Learning a Mahalanobis distance metric for data clustering and classification. Pattern Recogn 41(12):3600–3612
Nie F, Xiang S, Jia Y et al (2009) Semi-supervised orthogonal discriminant analysis via label propagation. Pattern Recogn 42(11):2615–2627
Nie F, Xiang S, Song Y et al (2009) Extracting the optimal dimensionality for local tensor discriminant analysis. Pattern Recogn 42(1):105–114
Zhang C, Nie F, Xiang S (2010) A general kernelization framework for learning algorithms based on kernel PCA. Neurocomputing 73(4):959–967
Basu S, Banerjee A, Mooney R (2004) Active semi-supervision for pairwise constrained clustering. In: Proceedings of the fourth SIAM international conference on data mining, pp 333–344
Cevikalp H, Verbeek J, Jurie F, Klaser A (2008) Semi-supervised dimensionality reduction using pairwise equivalence constraints. In: Proceedings of the 3rd international conference on computer vision theory and applications, pp 489–496
Mahdieh SB, Saeed BS (2009) Semi-supervised metric learning using pairwise constraints. In: International joint conference on artificial intelligence, pp 1217–1222
Zhang Z, Zhao M, Chow TWS (2012) Marginal semi-supervised sub-manifold projections with informative constraints for dimensionality reduction and recognition. Neural Netw 36:97–111
Davidson I, Wagstaff K, Basu S (2006) Measuring constraint-set utility for partitional clustering algorithms. In: Proceedings of the 10th European conference on principles and practice of knowledge discovery in databases, pp 115–126
Davidson I (2012) Two approaches to understanding when constraints help clustering. In: Proceedings of the 18th ACM international conference on knowledge discovery and data mining, pp 1312–1320
Wagstaff K (2007) Value, cost, and sharing: open issues in constrained clustering. In: International workshop on knowledge discovery in inductive databases, pp 1–10
Qi M, Xiang Y (2013) Semi-supervised sparsity pairwise constraint preserving projections based on GA. Appl Math 7(3):1065–1075
Cai X, Wen G, Wei J et al (2014) Relative manifold based semi-supervised dimensionality reduction. Front Comput Sci 8(6):923–932
Chrysouli C, Tefas A (2015) Spectral clustering and semi-supervised learning using evolving similarity graphs. Appl Soft Comput 34:625–637
Bar-Hillel A, Hertz T, Shental N, Weinshall D (2003) Learning distance functions using equivalence relations. International conference on machine learning, pp 11–18
Hoi SCH, Liu W, Lyu MR, Ma WY (2006) Learning distance metrics with contextual constraints for image retrieval. Conference on computer vision and pattern recognition, pp 2072–2078
Bar-Hillel A, Hertz T, Shental N, Weinshall D (2005) Learning a mahalanobis metric from equivalence constraints. J Mach Learn Res 6(6):937–965
Zhang D, Zhou ZH, Chen S (2007) Semi-supervised dimensionality reduction. In: SIAM conference on data Mining, pp 629–634
Wei J, Peng H (2008) Local and global preserving based semi-supervised dimensionality reduction method. J Softw 19(11):2833–2842
Wang N, Li X, Cui Y, Pan JS (2010) Instance-level based discriminative semi-supervised dimensionality reduction with chunklets. Int J Innov Comput Info Control 6(8):3763–3773
Li X, Luo JP, Chen MR, Wang N (2012) An improved shuffled frog-leaping algorithm with extremal optimization for continuous optimization. Info Sci 192(6):143–151
Song Y, Nie F, Zhang C et al (2008) A unified framework for semi-supervised dimensionality reduction. Pattern Recogn 41(9):2789–2799
Wan J, Yang M, Gao Y et al (2014) Pairwise costs in semisupervised discriminant analysis for face recognition. IEEE Trans Info Forensics Secur 9(10):1569–1580
Yan S, Bouaziz S, Lee D et al (2012) Semi-supervised dimensionality reduction for analyzing high-dimensional data with constraints. Neurocomputing 76(1):114–124
Settles B (2010) Active learning literature survey. Univ Wisconsin Madison 52(55–66):11
Mallapragada PK, Jin R, Jain AK (2008) Active query selection for semi-supervised clustering. In: Proceedings of the 19th international conference on pattern recognition, pp 1–4
Xu Q, Wagstaff KL (2005) Active constrained clustering by examining spectral eigenvectors. Discovery Science. Springer, Berlin Heidelberg, pp 294–307
Greene D, Cunningham P (2007) Constraint selection by committee: an ensemble approach to identifying informative constraints for semi-supervised clustering. In: Proceedings of the 18th European conference on machine learning, pp 17–21
Vu VV, Nicolas L (2012) Improving constrained clustering with active query selection. Pattern Recogn 45(4):1749–1758
Małgorzata C (2012) Boosting, bagging and fixed fusion methods performance for aiding diagnosis. Biocybern Biomed Eng 32(2):17–31
Yu G, Zhang G, Domeniconi C et al (2012) Semi-supervised classification based on random subspace dimensionality reduction. Pattern Recogn 45(3):1119–1135
Zhang D, Chen S, Zhou ZH, Yang Q (2008) Constraint projections for ensemble learning. In: Proceedings of the 23rd AAAI conference on artificial intelligence, pp 758–763
Sun D, Zhang D (2010) Bagging constraint score for feature selection with pairwise constraints. Pattern Recogn 43(6):2106–2118
Zhang Z, Zhao M, Chow TWS (2015) Graph based constrained semi-supervised learning framework via label propagation over adaptive neighborhood. IEEE Trans Knowl Data Eng 27(9):2362–2376
Guo YF, Li SJ, Yang JY et al (2003) A generalized Foley-Sammon transform based on generalized fisher discriminant criterion and its application to face recognition. Pattern Recogn Lett 24(1):147–158
Xiang S, Nie F, Zhang C (2008) Learning a Mahalanobis distance metric for data clustering and classification. Pattern Recogn 41(12):3600–3612
Wang H, Yan S, Xu D et al (2007) Trace ratio vs. ratio trace for dimensionality reduction. In: IEEE conference on computer vision and pattern recognition, pp 1–8
Jia Y, Nie F, Zhang C (2009) Trace ratio problem revisited. IEEE Trans Neural Netw 20(4):729–735
Zhang Z, Chow TWS, Zhao M (2013) Trace ratio optimization-based semi-supervised nonlinear dimensionality reduction for marginal manifold visualization. IEEE Trans Knowl Data Eng 25(5):1148–1161
Acknowledgments
This work is supported by the National Science Foundation of China under Grant Nos. 60902069, 61171124, 61502315, Supported by Science Technology Planning Project of Shenzhen (Grant Nos. 2011B010200045, JC201105170613A, JCYJ20130329110601621).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, N., Li, X. & Chen, P. Global and local scatter based semi-supervised dimensionality reduction with active constraints selection in ensemble subspaces. Pattern Anal Applic 20, 733–747 (2017). https://doi.org/10.1007/s10044-016-0530-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-016-0530-6