基于典型相关分析的多视图降维算法综述

doi:10.19678/j.issn.1000-3428.0053147

摘要/Abstract

摘要： 随着数据采集技术的发展，人们获取数据的途径呈多样化，所得到的数据往往具有多个视图，从而形成多视图数据。利用多视图数据不同的信息特征，设计相应的多视图学习策略以提高分类器的性能是多视图学习的研究目标。为更好地利用多视图数据，促进降维算法在实际中的应用，对多视图降维算法进行研究。分析多视图数据和多视图学习，在典型相关分析（CCA）的基础上追溯多视图CCA和核CCA，介绍多视图降维算法从两个视图到多个视图以及从线性到非线性的演化过程，总结各种融入判别信息和近邻信息的多视图降维算法，以更好地学习多视图降维算法。在此基础上，对比分析多视图降维算法的特点及存在的问题，并对未来的研究方向进行展望。

关键词: 多视图学习, 典型相关分析, 监督学习, 广义特征值, 降维

Abstract: With the development of data acquisition technology and the diversification of data obtaining approaches,the obtained data often have multiple views,so the multi-view data are formed.To study the information contained in these data becomes an research objective of multi-view learning.In order to make better use of multi-view data and improve the practical application of dimension reduction algorithms,this paper conducts a research on multi-view dimension reduction algorithms.This paper first reviews multi-view data and multi-view learning,and then,on the basis of Canonical Correlation Analysis(CCA),MCCA and KCCA are reviewed as well.Moreover,the evolution of multi-view dimension reduction algorithms,from two-view data to multi-view data and from linear to nonlinear is introduced herein.Then,this paper further summarizes various multi-view dimension algorithms integrating discriminant information and nearest neighbor information,so as to have a better understanding of these algorithms.Finally,this paper analyzes the characteristics and drawbacks of the multi-view dimension reduction algorithms and proposes future research directions.

Key words: multi-view learning, Canonical Correlation Analysis(CCA), supervised learning, generalized eigenvalue, dimension reduction

中图分类号:

TP18

张恩豪, 陈晓红, 刘鸿, 朱玉莲. 基于典型相关分析的多视图降维算法综述[J]. 计算机工程, 2020, 46(2): 1-10.

ZHANG Enhao, CHEN Xiaohong, LIU Hong, ZHU Yulian. Overview of Multi-view Dimension Reduction Algorithm Based on Canonical Correlation Analysis[J]. Computer Engineering, 2020, 46(2): 1-10.

https://www.ecice06.com/CN/Y2020/V46/I2/1

图/表 8

20200218140326

20200218140331

20200218140334

20200218140337

20200218140342

20200218140347

20200218140350

20200218140353

参考文献

[1] SU Shuzhi.Theoretical research and application of multi-view canonical correlation analysis[D].Wuxi:Jiangnan University,2017.(in Chinese) 苏树智.多视图典型相关分析的理论研究和应用[D].无锡:江南大学,2017.
[2] RUPING S,SCHEFFER T.Learning with multiple views[J].Multiple Views,2005,27(1):203-233.
[3] XU Chang,TAO Dacheng,XU Chao.A survey on multi-view learning[EB/OL].[2018-10-20].http://www.oalib.com/paper/4064776.
[4] ZHOU Zhihua,WANG Jue.Machine learning and its applications[M].Beijing:Tsinghua University Press,2011.(in Chinese) 周志华,王珏.机器学习及其应用[M].北京:清华大学出版社,2011.
[5] COLWELL R P.Applied multivariate statistical analysis[M].Berlin,Germany:Springer,2012.
[6] NIELSENA A.Multiset canonical correlations analysis and multispectral,truly multi-temporal remote sensing data[J].IEEE Transactions on Image Processing,2002,11(3):293-305.
[7] YAROWSKY D.Unsupervised word sense disambiguation rivaling supervised methods[C]//Proceedings of IEEE Annual Meeting of the Association for Computational Linguistics.Washington D.C.,USA:IEEE Press,1995:189-196.
[8] LIU Yanxun.Multi-view learning research and its algorithm improvement[D].Xi’an:Xidian University of Electronic Technology,2015.(in Chinese) 刘彦勋.多视图学习研究及其算法改进[D].西安:西安电子科技大学,2015.
[9] CHEN Xiaohong.Generalized correlation analysis research of data dimensionality reduction[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2011.(in Chinese) 陈晓红.数据降维的广义相关分析研究[D].南京:南京航空航天大学,2011.
[10] BELLMAN R.Adaptive control processes:a guided tour[M].Princeton,USA:Princeton University Press,1961.
[11] YANG Pei,GAO Wei.Multi-view discriminant transfer learning[C]//Proceedings of International Joint Conference on Artificial Intelligence.[S.1.]:AAAI Press,2013:1848-1854.
[12] TAN Ben.Multi-transfer:transfer learning with multiple views and multiple sources[J].Statistical Analysis and Data Mining,2014,7(4):282-293.
[13] ZHANG Dan,HE Jingrui,LIU Yan,et al.Multi-view transfer learning with a large margin approach[C]//Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2011:1208-1216.
[14] LUO Yong’en,HU Jicheng,XU Qian.Multimodal correlation feature processing method based on hypergraph[J].Computer Engineering,2017,43(1):226-230.(in Chinese) 罗永恩,胡继承,徐茜.基于超图的多模态关联特征处理方法[J].计算机工程,2017,43(1):226-230.
[15] GONEN M,GONEN G B,GURGEN F.Bayesian multi-view dimensionality reduction for learning predictive subspaces[J].Frontiers in Artificial Intelligence & Applications,2014,263:387-392.
[16] EATON E,DESJANDINS M,JACOB S.Multi-view clustering with constraint propagation for learning with an incomplete mapping between views[C]//Proceedings of ACM International Conference on Information and Knowledge Management.New York,USA:ACM Press,2010:125-136.
[17] LIU Jianwei,LI Shuangcheng,LUO Xionglin.Research of sampling-based multi-modal distribution clustering algorithm[J].Computer Engineering,2010,36(24):153-155.(in Chinese) 刘建伟,李双成,罗雄麟.基于抽样的多模态分布聚类算法研究[J].计算机工程,2010,36(24):153-155.
[18] LI Yeqing,NIE Feiping,HUANG Heng,et al.Large-scale multi-view spectral clustering via bipartite graph[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press,2015:568-575.
[19] DU Mingyang,BI Daping,WANG Shuliang.Multiple target tracking algorithm based on adaptive IMM algorithm in clutter[J].Modern Radar,2018,40(7):47-53.(in Chinese) 杜明洋, 毕大平,王树亮.杂波背景下自适应IMM机动目标跟踪算法[J].现代雷达,2018,40(7):47-53.
[20] DING Xuan.Multimodal biometric identification tech-nology and its standardization trends[J].computer knowledge and technology,2017,13(36):153-154.(in Chinese) 丁璇.多模态生物特征识别技术及其标准化动态[J].电脑知识与技术, 2017, 13(36):153-154.
[21] SUN Shiliang.Multi-view laplacian support vector machines[J].Applied Intelligence,2013,41(4):209-222.
[22] TAO Hong,HOU Chengping,NIE Feiping,et al.Scalable multi-view semi-supervised classification via adaptive regression[J].IEEE Transactions on Image Processing,2017,26(9):4283-4296.
[23] XIE Xijiong,SUN Shiliang.Multi-view Laplacian twin support vector machines[J].Applied Intelligence,2014,41(4):1059-1068.
[24] ZHANG Liang,MA Bingpeng.Adaptively unified semi-supervised learning for cross-modal retrieval[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence.Washington D.C.,USA:IEEE Press,2017:354-365.
[25] JIN Xin,ZHUANG Fuzhen,WANG Shuhui,et al.Shared structure learning for multiple tasks with multiple views[C]//Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases.Berlin,Germany:Springer,2013:353-368.
[26] CHEN Jianhui,TANG Lei,LIU Jun,et al.A convex formulation for learning shared structures from multiple tasks[C]//Proceedings of International Conference on Machine Learning.New York,USA:ACM Press,2009:137-144.
[27] CAO Xiaochun,ZHANG Changqiang,FU Huazhu,et al.Diversity-induced multi-view subspace clustering[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:586-594.
[28] WILCOX R R.Testing the hypothesis of independence two stes of variates[J].Multivariate Behavioral Research,1995,30(2):213-225.
[29] ANDERSON T W.Relations between two sets of variates[J].Biometrike,1936,28(3/4):151-161.
[30] HOTELING H.Relations between two sets of variates[J].Biometrika,1936,28(3/4):321-377.
[31] EFRON B.Canonical analysis of several sets of variables[J].Biometrika,1971,58(3):433-451.
[32] SUN Tingkai,CHEN Songcan,YANG Jingyu,et al.A novel method of combined feature extraction for recognition[C]//Proceedings of the 8th IEEE International Conference on Data Mining.[S.1.]:IEEE Computer Society,2008:1043-1048
[33] GAO Lei,QI Lin,CHEN Enqing,et al.Discriminative multiple canonical correlation analysis for multi-feature information fusion[C]//Proceedings of IEEE ISM’12.Washington D.C.,USA:IEEE Press,2012:36-43.
[34] MELZER T,REITER M,BISCHOF H.Kernel canonical correlation analysis[J].Journal of Financial Economic Policy,2001,6(2):179-196.
[35] SUN Tingkai,CHEN Songcan,JIN Zhong,et al.Kernelized discriminative canonical correlation analysis[C]//Proceedings of International Conference on Wavelet Analysis and Pattern Recognition.Washington D.C.,USA:IEEE Press,2008:1283-1287.
[36] YU Kai,YU Shipeng.Multi-output regularized feature projection[J].IEEE Transactions on Knowledge and Data Engineering,2006,18(12):1600-1613.
[37] PENG Yan,ZHANG Daoqiang,ZHANG Jianchuan.A new canonical correlation analysis algorithm with local discrimina-tion[J].Neural Processing Letters,2010,31(1):1-15.
[38] SHARMA A,KUMAR A,DAUME H,et al.Generalized multi-view analysis:a discriminative latent space[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.[S.1.]:IEEE Computer Society,2012:2160-2167.
[39] KIM T K,KITTLER J,CIPOLLA R.Discriminative learning and recognition of image set classes using canonical correlations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(6):1005-1018.
[40] ZHENG Wenming,ZHOU Xiaoyan,ZOU Cairong,et al.Facial expression recognition using kernel canonical correlation analysis[J].IEEE Transactions on Neural Networks,2006,17(1):233-238.
[41] VLASSIS N,MOTOMURA Y,KROSE B.Supervised linear feature extraction for mobile robot localization[C]//Proceedings of IEEE International Conference on Robotics and Automation.Washington D.C.,USA:IEEE Press,2000:2979-2984.
[42] MELZER T,REITER M,BICSHOF H.Appearance models based on kernel canonical correlation analysis[J].Pattern Recognition,2003,36(9):1961-1971.
[43] ABRAHAM B,MEROLA G.Dimensionality reduction approach to multivariate prediction[J].Canadian Journal of Statistics,2001,29(2):191-200.
[44] ZHANG Fan.Partial differential equation and edge detection based image denoising algorithm[J].Computer Engineering and Design, 2014,35(2):562-566.(in Chinese) 张帆.基于偏微分方程与边缘检测的图像去噪算法[J].计算机工程与设计,2014,35(2):562-566.
[45] HARDOON D,SZEDMAK S,SHAWE-TAYLOR J.Canonical correlation analysis:an overview with application to learning methods[J].Neural Computation,2004,16(12):2639-2664.
[46] LI Y,SHAWE-TAYLOR J.Using KCCA for Japanese English cross-language information retrieval and document classification[J].Journal of Intelligent Information Systems,2006,27(2):117-133.
[47] FUKUMIZU K,BACH F R.Statistical consistency of kernel canonical correlation analysis[J].Journal of Machine Learning Research,2007(8):361-383.
[48] VAPNIK V N.An overview of statistical learning theory[J].IEEE Transactions on Neural Networks,1999,10(5):988-999.
[49] MELZER T,REITER M,BISCHOF H.Kernel canonical correlation analysis[J].Journal of Financial Economic Policy,2012,6(2):179-196.
[50] MIKA S,RATSCH G,WESTON J,et al.Fisher discriminant analysis with kernels[C]//Proceedings of IEEE Workshop on Neural Networks for Signal Processing.Washington D.C.,USA:IEEE Press,1999:41-48.
[51] BURGES C J C,SMOLA A J.Advances in kernel methods:support vector learning[M].[S.1.]:MIT Press,1999.
[52] ARAKI T,HINO H,AKAHO S.A kernel method to extract common features based on mutual information[M].Berlin,Germany:Springer,2014:26-34.
[53] LONG Mingsheng,WANG Jianmin,DING Guiguang,et al.Transfer joint matching for unsupervised domain adaptation[C]//Proceedings of International Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:1410-1417.
[54] BELHUNEUR P N,HESPANHA J P,KRIEGMAN D J.Fisherfaces:recognition using class specific linear projection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,19(7):711-720.
[55] KIM T K,KITTLER J,CIPOLLA R.Learning discriminative canonical correlations for object recognition with image sets[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2006:251-262.
[56] FUKUI K,YAMAGUCHI O.Face recognition using multi-viewpoint patterns for robot vision[C]//Proceedings of the 20th International Symposium on Robotics Research.Berlin,Germany:Springer,2005:192-201.
[57] YAMAGUCHI O,FUKUI K,MAEDA K.Face recognition using temporal image sequence[C]//Proceedings of the 3rd IEEE International Conference on Automatic Face and Gesture Recognition.Washington D.C.,USA:IEEE Press,1998:318-326.
[58] WOLF L,SHASHUA A.Learning over sets using kernel principal angles[J].Journal of Machine Learning Research,2004,4(6):913-931.
[59] KIM T K,ARANDJELOVIC O,CIPOLLA R.Boosted manifold principal angles for image set-based recognition[J].Pattern Recognition,2007,40(9):2475-2484.
[60] BRESSAN M,VITRIA J.Nonparametric discriminant analysis and nearest neighbor classification[J].Pattern Recognition Letters,2003,24(15):2743-2749.
[61] KAN Meina,SHAN Shiguang,ZHANG Haihong,et al.Multi-view discriminant analysis[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2012:808-821.
[62] DUDA R O,HART P E,STORK D G.Pattern classification[M].[S.1.]:Wiley-Interscience,2001.
[63] YOU Xingge,XU,Jiamiao,YUAN Wei,et al.Multi-view common component discriminant analysis for cross-view classification[J].Pattern Recognition,2019,92:37-51.
[64] XIE Xijiong, SUN Shiliang.Multi-view twin support vector machines[J].Intelligent Data Analysis,2015,19(4):701-712.
[65] SUN Tingkai.Research and application of enhanced canonical correlation analysis[D].Nanjing:Nanjing University of Aeronautics and Astronautics,2006.(in Chinese) 孙廷凯.增强型典型相关分析研究与应用[D].南京:南京航空航天大学,2006.
[66] SUN Shiliang,CHAO Guoqing.Multi-view maximum entropy discrimination[C]//Proceedings of the 23th International Joint Conference on Artificial Intelligence.Washington D.C.,USA:IEEE Press,2013:1706-1712.
[67] SIM T,BAKER S,BSAT M.The CMU pose,illumination,and expression database[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(12):1615-1618.
[68] PHILLIPS P J,MOON H,RIZVI,S.A,et al.The FERET evaluation methodology for face-recognition algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(10):1090-1104.
[69] LI S Z,LEI Z,AO M.The HFB face database for heterogeneous face biometrics research[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2009:1-8.
[70] SAMARIA F S,HARTER A C.Parameterization of a stochastic model for human face identification[C]//Proceedings of the 2nd IEEE Workshop on Applications of Computer Vision.Washington D.C.,USA:IEEE Press,1994:138-142.
[71] HORIKAWA Y.Use of autocorrelation kernels in kernel canonical correlation analysis for texture classification[C]//Proceedings of International Conference on Neural Information Processing.Berlin,Germany:Springer,2004:1235-1240.
[72] TENENBAUM J B,SILVA V D,LANGFORD J C.A global geometric framework for nonlinear dimensionality reduction[J].Science,2000,290:2319-2323.
[73] MU Lisheng,LÜ Yingchun.Face recognition method based on sparse representation and feature fusion[J].Modern Electronics Technique,2018,41(9):83-86.(in Chinese) 木立生,吕迎春.基于稀疏表示与特征融合的人脸识别方法[J].现代电子技术,2018,41(9):83-86.
[74] LU Yichao,FOSTER D P.Large scale canonical correlation analysis with iterative least squares[C]//Proceedings of International Conference on Neural Information Processing Systems.[S.1.]: MIT Press,2014:91-99.
[75] PARKHOMENKO E,TRITCHLER D,BEYENE J.Sparse canonical correlation analysis with application to genomic data integration[J].Statistical Applications in Genetics and Molecular Biology,2009,8(1):1-34.
[76] DU Changshun,HUANG Lei.Sentiment analysis with piecewise convolution neural network[J].Computer Engineering and Science,2017,39(1):173-179.(in Chinese) 杜昌顺,黄磊.分段卷积神经网络在文本情感分析中的应用[J].计算机工程与科学,2017,39(1):173-179.
[77] YU Donghang,ZHANG Baoming,GUO Haitao,et al.Joint salient feature and convolutional neural network for ship detection in remote sensing images[J].Journal of Image and Graphics,2018,23(12):1947-1958.(in Chinese) 余东行,张保明,郭海涛,等.联合显著性特征与卷积神经网络的遥感影像舰船检测[J].中国图象图形学报,2018,23(12):1947-1958.
[78] ANDREW G,ARORA R,BILMES J,et al.Deep canonical correlation analysis[C]//Proceedings of 30th International Conference on Machine Learning.Georgia,USA:[s.n.],2013:1247-1255.
[79] LI Shaoyun,JIANG Yuan,ZHOU Zhuihua.Partial multi-view clustering[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press,2014:1968-1974.
[80] SHAO W,HE L,PHILIP S Y.Multiple incomplete views clustering via weighted nonnegative matrix factorization with L_2,1 regularization[C]//Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases.Berlin,Germany:Springer,2015:318-334.
[81] LUO Y,TAO D,RAMAMOHANARAO K,et al.Tensor canonical correlation analysis for multi-view dimension reduction[J].IEEE transactions on Knowledge and Data Engineering,2015,27(11):3111-3124.

选择文件类型/文献管理软件名称

选择包含的内容