《计算机应用研究》|Application Research of Computers

基于属性自表达的低秩超图属性选择算法

Low rank hypergraph feature selection algorithm based on self-representation

免费全文下载 (已被下载 次)  
获取PDF全文
作者 苏毅娟,雷聪,胡荣耀,何威,朱永华
机构 1.广西师范学院 计算机与信息工程学院,南宁 530023;2.广西师范大学 广西多源信息挖掘与安全重点实验室,广西 桂林 541004;3.广西大学 计算机与电子信息学院,南宁 530004
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)08-2294-05
DOI 10.3969/j.issn.1001-3695.2017.08.012
摘要 针对高维数据具有低秩形式和属性冗余等特点,提出一种基于属性自表达的无监督超图属性选择算法。该算法首先利用属性自表达特点用其他属性稀疏地表达每个属性,此自表达形式使用低秩假设寻找高维数据的低秩表示,然后建立超图正则化因子保持高维数据的局部结构,最后利用稀疏正则化因子进行属性选择。属性自表达特性确定属性的重要性,低秩表示相当于考虑数据的全局信息进行子空间学习,超图正则化因子考虑数据的局部结构对数据进行子空间学习。该算法实际上考虑数据全局和局部信息进行子空间学习,更是一种嵌入了子空间学习的属性选择算法。实验结果表明,该算法相比其他对比算法,能更有效地选取属性,并能取得很好的分类效果。
关键词 属性选择;属性自表达;子空间学习;超图;低秩表示
基金项目 国家自然科学基金资助项目(61450001,61263035,61573270)
国家“973”计划资助项目(2013CB329404)
中国博士后科学基金资助项目(2015M570837)
广西自然科学基金资助项目(2012GXNSFGA060004,2015GXNSFCB139011,2015GXNSFAA139306)
广西研究生教育创新计划项目(YCSZ2016045,YCSZ2016046,XYCSZ2017064,XYCSZ2017067,YCSW2017065)
本文URL http://www.arocmag.com/article/01-2017-08-012.html
英文标题 Low rank hypergraph feature selection algorithm based on self-representation
作者英文名 Su Yijuan, Lei Cong, Hu Rongyao, He Wei, Zhu Yonghua
机构英文名 1.CollegeofComputer&InformationEngineering,GuangxiTeachersEducationUniversity,Nanning530023,China;2.GuangxiKeyLaboratoryofMultisourceInformationMining&Security,GuangxiNormalUniversity,GuilinGuangxi541004,China;3.SchoolofComputer,Electronics&Information,GuangxiUniversity,Nanning530004,China
英文摘要 Due to that high-dimensional data usually is low-rank and contains redundant features, this paper proposed a novel unsupervised hypergraph feature selection algorithm based on self-representation property of features. First, it considered the self-representation matrix to sparsely represent each feature by a linear combination of other features. Such self-representation property was then enforced a low-rank assumption to learn the low-rank representation of high-dimensional data, via conside-ring the global structure of the data to conduct subspace learning. Second, it considered the local structure of the data by a hypergraph based regularizer. In this way, the proposed method integrated subspace learning into the framework of feature selection. Experimental results demonstrate that the proposed can select the best discriminative features and achieve the best classification performance, compared to the competing methods.
英文关键词 feature selection; self-representation; subspace learning; hypergraph; low-rank representation
参考文献 查看稿件参考文献
  [1] Zhang Shichao, Jin Zhi, Zhu Xiaofeng. Missing data imputation by utilizing information within incomplete instances[J] . Journal of Systems and Software, 2011, 84(3):452-459.
[2] Zhu Xiaofeng, Huang Zi, Shen Hengtao, et al. Dimensionality reduction by mixed kernel canonical correlation analysis[J] . Pattern Re-cognition, 2012, 45(8):3003-3016.
[3] Zhu Xiaofeng, Zhang Shichao, Jin Zhi, et al. Missing value estimation for mixed-attribute datasets[J] . IEEE Trans on Knowledge and Data Engineering, 2011, 23(1):110-121.
[4] Zhao Yanchang, Zhang Shichao. Generalized dimension-reduction framework for recent-biased time series analysis[J] . IEEE Trans on Knowledge & Data Engineering, 2006, 18(2):231-244.
[5] Zhu Xiaofeng, Suk H I, Shen Dinggang. Matrix-similarity based loss function and feature selection for Alzheimer's disease diagnosis[C] //Proc of IEEE Conference on Computer Vision and Pattern Recognition. 2014:3089-3096.
[6] Zhu Xiaofeng, Huang Zi, Yang Yang, et al. Self-taught dimensionality reduction on the high-dimensional small-sized data[J] . Pattern Re-cognition, 2013, 46(1):215-229.
[7] Pyatykh S, Hesser J, Lei Zheng. Image noise level estimation by principal component analysis[J] . IEEE Trans on Image Processing, 2013, 22(2):687-699.
[8] Fan Zizhu, Xu Yong, Zhang D. Local linear discriminant analysis framework using sample neighbors[J] . IEEE Trans on Neural Networks, 2011, 22(7):1119-1132.
[9] Zhu Xiaofeng, Li Xuelong, Zhang Shichao. Block-row sparse multi-view multilabel learning for image classification[J] . IEEE Trans on Cybernetics, 2016, 46(2):450-461.
[10] Qin Yongsong, Zhang Shichao, Zhu Xiaofeng, et al. Semi-parametric optimization for missing data imputation[J] . Applied Intelligence, 2007, 27(1):79-88.
[11] Zhang Shichao, Zhang Chengqi, Yang Qiang. Data preparation for data mining[M] . [S. l. ] :Academic Press, 1999.
[12] Liimatainen K, Heikkila R, Yli-Harja O. Sparse logistic regression and polynomial modelling for detection of artificial drainage networks[J] . Remote Sensing Letters, 2015, 6(4):311-320.
[13] Lai Hanjiang, Pan Yan, Liu Cong, et al. Sparse learning-to-rank via an efficient primal-dual algorithm[J] . IEEE Trans on Computers, 2013, 62(6):1221-1233.
[14] Zhu Xiaofeng, Zhang Shichao, Zhang Jilian, et al. Cost-sensitive imputing missing values with ordering[C] //Proc of AAAI Conference on Artificial Intelligence. 2007:1922-1923.
[15] Wu Xindong, Zhang Chengqi, Zhang Shichao. Efficient mining of both positive and negative association rules[J] . ACM Trans on Information Systems, 2004, 22(3):381-405.
[16] Zhou Dengyong, Huang Jiayuan, Bernhard S. Learning with hyper-graphs:clustering, classification, and embedding[C] //Advances in Neural Information Processing Systems. 2006:1601-1608.
[17] Zhang Chengqi, Qin Yongsong, Zhu Xiaofeng, et al. Clustering-based missing value imputation for data preprocessing[C] //Proc of IEEE International Conference on Industrial Informatics. 2006:1081-1086.
[18] Ling C X, Yang Qiang, Wang Jianning, et al. Decision trees with mini-mal costs[C] // Proc of International Conference on Machine Lear-ning. 2004:4-8.
[19] Chen Y M, Chiang J H. Face recognition using combined multiple feature extraction based on Fourier-Mellin approach for single example image per person[J] . Pattern Recognition Letters, 2010, 31(13):1833-1841.
[20] UCI repository of machine learning datasets[EB/OL] . [2016-05-27] . http://archive. ics. uci. edu/ml/.
[21] Feature selection datasets[EB/OL] . [2016-05-27] . http://feat-ureselection. asu. edu/datasets. Php.
[22] LIBSVM:a library for support vector machines[EB/OL] . [2016-05-27] . http://www. csie. ntu. edu. tw/~cjlin/libs-vm.
[23] Zhu Pengfei, Zuo Wangmeng, Zhang Lei, et al. Unsupervised feature selection by regularized self-representation[J] . Pattern Recognition, 2015, 48(2):438-446.
收稿日期 2016/5/27
修回日期 2016/7/5
页码 2294-2298
中图分类号 TP391
文献标志码 A