A New Locality-Preserving Canonical Correlation Analysis Algorithm for Multi-View Dimensionality Reduction

详细信息    查看全文

• 作者：Fengshan Wang (1)
  Daoqiang Zhang (1)
  
• 关键词：Locality preserving projection ; Canonical correlation analysis ; Multi ; view dimensionality reduction ; High ; dimensional classification
• 刊名：Neural Processing Letters
• 出版年：2013
• 出版时间：April 2013
• 年：2013
• 卷：37
• 期：2
• 页码：135-146
• 全文大小：264 KB
• 参考文献：1. Long B, Yu PS, Zhang ZM (2008) A general model for multiple view unsupervised learning. In: Proceedings of the 2005 SIAM international conference on data mining (SDM). SIAM, Newport Beach, p 822鈥?33
  2. Zhang D, Wang F, Zhang C, Li (2008) T Multi-view local learning. In: Proceedings of the 23rd AAAI conference on artificial intelligence (AAAI). AAAI, Chicago, p 752鈥?57
  3. Brefeld U, B眉scher C, Scheffer T (2005) Multi-view discriminative sequential learning. In: Proceedings of the 2005 European conference on machine learning (ECML). Springer, Berlin, p 60鈥?1
  4. Sindhwani V, Rosenberg DS (2008) An rkhs for multi-view learning and manifold co-regularization. In: Proceedings of the 25th international conference on machine learning (ICML). ACM, Edinburgh, p 976鈥?83
  5. Huopaniemi I, Suvitaival T, Nikkil盲 J, Ore拧i膷 M, Kaski S (2009) Multi-way, multi-view learning. In: NIPS workshop on learning from multiple sources with applications to robotics. NIPS, Whistler
  6. Diethe T, Hardoon DR, Shawe-Taylor J (2008) Multiview Fisher discriminant analysis. In: NIPS workshop on learning from multiple sources. NIPS, Whistler
  7. Hotelling H (1936) Relation between two sets of variables. Biometrica 28: 322鈥?77
  8. Jolliffe IT (2002) Principal component analysis, 2nd edn. Springer, New York
  9. Nielsen AA (2002) Multiset canonical correlations analysis and multispectral, truly multitemporal remote sensing data. IEEE Trans Image Process 11(3): 293鈥?05 CrossRef
  10. Theodoridis S, Koutroumbas K (2006) Pattern recognition, 3rd edn. Academic Press, Orlando
  11. Sun Q-S, Zeng S-G, Liu Y, Heng P-A, Xia D-S (2005) A new method of feature fusion and its application in image recognition. Pattern Recognit 38(12): 2437鈥?448 CrossRef
  12. Hel-Or Y (2004) The canonical correlations of color images and their use for demosaicing. Technical report. HP Laboratories, Israel
  13. Hardoon DR, Szedm谩k S, Shawe-Taylor J (2004) Canonical correlation analysis: an overview with application to learning methods. Neural Comput 16(12): 2639鈥?664 CrossRef
  14. Abraham B, Merola G (2005) Dimensionality reduction approach to multivariate prediction. Comput Stat Data Anal 48(1): 5鈥?6 CrossRef
  15. Hsieh WW (2000) Nonlinear canonical correlation analysis by neural networks. Neural Netw 13(10): 1095鈥?105 CrossRef
  16. Yamada M, Azimi-Sadjadi MR (2005) Nonlinear signal estimation using kernel wiener filter in canonical correlation analysis framework. In: Proceedings of the international conference on computational intelligence for modelling, control and automation. IEEE, Vienna, p 1095鈥?101
  17. Fukumizu K, Bach F, Gretton A (2007) Consistency of kernel canonical correlation analysis. J Mach Learn Res 8: 361鈥?83
  18. Emdad F, Kirby M, Zekavat SA (2008) Feature extraction via kernelized signal fraction analysis vs kernelized principal component analysis. In: Proceedings of the 2008 international conference on data mining (DMIN). CSREA Press, Pisa, p 180鈥?84
  19. Wu W, He J, Zhang J (2008) A kernelized discriminant analysis algorithm based on modified generalized singular value decomposition. In: Proceedings of IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, Taipei, p 1353鈥?356
  20. Zhang D-Q, Chen S-C (2003) Clustering incomplete data using kernel-based fuzzy c-means algorithm. Neural Process Lett 18(3): 155鈥?62 CrossRef
  21. Lai PL, Fyfe C (2000) Kernel and nonlinear canonical correlation analysis. In: Proceedings of the IEEE-INNS-ENNS international joint conference on neural networks (IJCNN), vol 4. IEEE, Como, p 614
  22. Fern XZ, Brodley CE, Friedl MA (2005) Correlation clustering for learning mixtures of canonical correlation models. In: Proceedings of the 2005 SIAM international conference on data mining (SDM). SIAM, Newport Beach, p 439鈥?46
  23. Klami A, Kaski S (2007) Local dependent components. In: Proceedings of the 24th international conference on machine learning (ICML), ACM, Edinburgh, p 425鈥?32
  24. Bach F, Jordan M (2006) A probalilistic interpretation of canonical correlation analysis. Technical report. Computer Science Division, University of California, Berkeley
  25. Roweis S, Saul L (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290: 2510鈥?522 CrossRef
  26. He X, Niyogi P (2003) Locality preserving projections. In: Advances in neural information processing systems. MIT Press, Cambridge
  27. Sun T, Chen S (2007) Locality preserving CCA with applications to data visualization and pose estimation. Image Vision Comput 25(5): 531鈥?43 CrossRef
  28. Hoegaerts L, Suykens JAK, Vandewalle J, Moor BD (2005) Subset based least squares subspace regression in RKHS. Neurocomputing 63: 293鈥?23 CrossRef
  29. Melzer T, Reiter M, Bischof H (2003) Appearance models based on kernel canonical correlation analysis. Pattern Recognit 36(9): 1961鈥?971 CrossRef
  30. Zhang J, Zhang D (2011) A novel ensemble construction method for multi-view data using random cross-view correlation between within-class examples. Pattern Recognit 44(6): 1162鈥?171 CrossRef
  
• 作者单位：Fengshan Wang (1)
  Daoqiang Zhang (1)
  
  1. Department of Computer Science and Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, China
  
• ISSN：1573-773X

文摘

Canonical correlation analysis (CCA) is a well-known technique for extracting linearly correlated features from multiple views (i.e., sets of features) of data. Recently, a locality-preserving CCA, named LPCCA, has been developed to incorporate the neighborhood information into CCA. Although LPCCA is proved to be better in revealing the intrinsic data structure than CCA, its discriminative power for subsequent classification is low on high-dimensional data sets such as face databases. In this paper, we propose an alternative formulation for integrating the neighborhood information into CCA and derive a new locality-preserving CCA algorithm called ALPCCA, which can better discover the local manifold structure of data and further enhance the discriminative power for high-dimensional classification. The experimental results on both synthetic and real-world data sets including multiple feature data set and face databases validate the effectiveness of the proposed method.