{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T23:04:54Z","timestamp":1768345494104,"version":"3.49.0"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2016,7,20]],"date-time":"2016-07-20T00:00:00Z","timestamp":1468972800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"U.S","award":["NSF-IIS 1117965, NSF-IIS 1302675, NSF-IIS 1344152, NSF-DBI 1356628 and NIH R01 AG049371"],"award-info":[{"award-number":["NSF-IIS 1117965, NSF-IIS 1302675, NSF-IIS 1344152, NSF-DBI 1356628 and NIH R01 AG049371"]}]},{"DOI":"10.13039\/501100012166","name":"973 program","doi-asserted-by":"crossref","award":["2015CB352302"],"award-info":[{"award-number":["2015CB352302"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Australian Research Council Discovery Projects","award":["DP140100545 and DP140102206"],"award-info":[{"award-number":["DP140100545 and DP140102206"]}]},{"DOI":"10.13039\/501100011818","name":"Data to Decisions Cooperative Research Centre www.d2dcrc.com.au","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100011818","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2017,2,28]]},"abstract":"<jats:p>Principal component analysis (PCA) has been widely applied to dimensionality reduction and data pre-processing for different applications in engineering, biology, social science, and the like. Classical PCA and its variants seek for linear projections of the original variables to obtain the low-dimensional feature representations with maximal variance. One limitation is that it is difficult to interpret the results of PCA. Besides, the classical PCA is vulnerable to certain noisy data. In this paper, we propose a Convex Sparse Principal Component Analysis (CSPCA) algorithm and apply it to feature learning. First, we show that PCA can be formulated as a low-rank regression optimization problem. Based on the discussion, the<jats:italic>l<\/jats:italic><jats:sub>2, 1<\/jats:sub>-normminimization is incorporated into the objective function to make the regression coefficients sparse, thereby robust to the outliers. Also, based on the sparse model used in CSPCA, an optimal weight is assigned to each of the original feature, which in turn provides the output with good interpretability. With the output of our CSPCA, we can effectively analyze the importance of each feature under the PCA criteria. Our new objective function is convex, and we propose an iterative algorithm to optimize it. We apply the CSPCA algorithm to feature selection and conduct extensive experiments on seven benchmark datasets. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art unsupervised feature selection algorithms.<\/jats:p>","DOI":"10.1145\/2910585","type":"journal-article","created":{"date-parts":[[2016,7,21]],"date-time":"2016-07-21T15:13:24Z","timestamp":1469114004000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":71,"title":["Convex Sparse PCA for Unsupervised Feature Learning"],"prefix":"10.1145","volume":"11","author":[{"given":"Xiaojun","family":"Chang","sequence":"first","affiliation":[{"name":"University of Technology, Sydney, Ultimo NSW, Australia"}]},{"given":"Feiping","family":"Nie","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, TX"}]},{"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Technology, Ultimo NSW, Australia"}]},{"given":"Chengqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Technology, Ultimo NSW, Australia"}]},{"given":"Heng","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Texas at Arlington, Arlington, TX"}]}],"member":"320","published-online":{"date-parts":[[2016,7,20]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Yu","author":"Aggarwal Cham C.","year":"2001"},{"key":"e_1_2_1_2_1","volume-title":"Dimakis","author":"Asteris Megasthenis","year":"2015"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.598228"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835848"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.89"},{"key":"e_1_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Xiaojun Chang Feiping Nie Yi Yang and Heng Huang. 2014. A convex formulation for semi-supervised multi-label feature selection. In AAAI. 1171--1177. Xiaojun Chang Feiping Nie Yi Yang and Heng Huang. 2014. A convex formulation for semi-supervised multi-label feature selection. In AAAI. 1171--1177.","DOI":"10.1609\/aaai.v28i1.8922"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2441735"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2010.272"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273519"},{"key":"e_1_2_1_10_1","volume-title":"Michael I. Jordan, and Gert R. G. Lanckriet.","author":"Aspremont Alexandre","year":"2004"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2003.808183"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.927464"},{"key":"e_1_2_1_13_1","unstructured":"Xiaofei He Deng Cai and Partha Niyogi. 2005. Laplacian score for feature selection. In NIPS. 507--514. Xiaofei He Deng Cai and Partha Niyogi. 2005. Laplacian score for feature selection. In NIPS. 507--514."},{"key":"e_1_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Chenyong Hu Benyu Zhang Shuicheng Yan Qiang Yang Jun Yan Zheng Chen and Wei-Ying Ma. 2004. Mining ratio rules via principal sparse non-negative matrix factorization. In ICDM. 407--410. Chenyong Hu Benyu Zhang Shuicheng Yan Qiang Yang Jun Yan Zheng Chen and Wei-Ying Ma. 2004. Mining ratio rules via principal sparse non-negative matrix factorization. In ICDM. 407--410.","DOI":"10.1109\/ICDM.2004.10062"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1198\/1061860032148"},{"key":"e_1_2_1_16_1","unstructured":"Rajiv Khanna Joydeep Ghosh Russell A. Poldrack and Oluwasanmi Koyejo. 2015. Sparse submodular probabilistic PCA. In AISTATS. 453--461. Rajiv Khanna Joydeep Ghosh Russell A. Poldrack and Oluwasanmi Koyejo. 2015. Sparse submodular probabilistic PCA. In AISTATS. 453--461."},{"key":"e_1_2_1_17_1","unstructured":"Abhisek Kundu Petros Drineas and Malik Magdon-Ismail. 2015. Approximating sparse PCA from incomplete data. In NIPS. 388--396. Abhisek Kundu Petros Drineas and Malik Magdon-Ismail. 2015. Approximating sparse PCA from incomplete data. In NIPS. 388--396."},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2400461"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.817413"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2187179"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.07.009"},{"key":"e_1_2_1_22_1","unstructured":"Baback Moghaddam Yair Weiss and Shai Avidan. 2005. Spectral bounds for sparse PCA: Exact and greedy algorithms. In NIPS. 915--922. Baback Moghaddam Yair Weiss and Shai Avidan. 2005. Spectral bounds for sparse PCA: Exact and greedy algorithms. In NIPS. 915--922."},{"key":"e_1_2_1_24_1","volume-title":"Ding","author":"Nie Feiping","year":"2010"},{"key":"e_1_2_1_25_1","volume-title":"Ding","author":"Nie Feiping","year":"2012"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2044958"},{"key":"e_1_2_1_27_1","unstructured":"Feiping Nie Jianjun Yuan and Heng Huang. 2014. Optimal mean robust principal component analysis. In ICML. 1062--1070. Feiping Nie Jianjun Yuan and Heng Huang. 2014. Optimal mean robust principal component analysis. In ICML. 1062--1070."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2661829.2661993"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.1987.10488218"},{"key":"e_1_2_1_30_1","doi-asserted-by":"crossref","unstructured":"Ferdinand Samaria and Andy Harter. 1994. Parameterisation of a stochastic model for human face identification. In WACV. 138--142. Ferdinand Samaria and Andy Harter. 1994. Parameterisation of a stochastic model for human face identification. In WACV. 138--142.","DOI":"10.1109\/ACV.1994.341300"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmva.2007.06.007"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2542182.2542197"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1162\/153244303321897735"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2629587"},{"key":"e_1_2_1_35_1","volume-title":"Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser. B (Methodol.)","author":"Tibshirani Robert","year":"1996"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2014.12.012"},{"key":"e_1_2_1_37_1","volume-title":"Sheng","author":"Wang Sen","year":"2015"},{"key":"e_1_2_1_38_1","volume-title":"Witten and Robert Tibshirani","author":"Daniela","year":"2012"},{"key":"e_1_2_1_39_1","unstructured":"John Wright Yigang Peng Yi Ma Arvind Ganesh and Shankar Rao. 2009. Robust principal component analysis: Exact recovery of corrupted low-rank matrices by convex optimization. In NIPS. 1943--1952. John Wright Yigang Peng Yi Ma Arvind Ganesh and Shankar Rao. 2009. Robust principal component analysis: Exact recovery of corrupted low-rank matrices by convex optimization. In NIPS. 1943--1952."},{"key":"e_1_2_1_40_1","unstructured":"Huan Xu Constantine Caramanis and Sujay Sanghavi. 2010. Robust PCA via outlier pursuit. In NIPS. 2496--2504. Huan Xu Constantine Caramanis and Sujay Sanghavi. 2010. Robust PCA via outlier pursuit. In NIPS. 2496--2504."},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.363442"},{"key":"e_1_2_1_42_1","unstructured":"Wenzhuo Yang and Huan Xu. 2015. A unified framework for outlier-robust PCA-like algorithms. In ICML. 484--493. Wenzhuo Yang and Huan Xu. 2015. A unified framework for outlier-robust PCA-like algorithms. In ICML. 484--493."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.5555\/2283516.2283660"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2011.107"},{"key":"e_1_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Xinhua Zhang Yaoliang Yu Martha White Ruitong Huang and Dale Schuurmans. 2011. Convex sparse coding subspace learning and semi-supervised extensions. In AAAI. 567--573. Xinhua Zhang Yaoliang Yu Martha White Ruitong Huang and Dale Schuurmans. 2011. Convex sparse coding subspace learning and semi-supervised extensions. In AAAI. 567--573.","DOI":"10.1609\/aaai.v25i1.7935"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.870645"},{"key":"e_1_2_1_47_1","unstructured":"Qian Zhao Deyu Meng Zongben Xu Wangmeng Zuo and Lei Zhang. 2014. Robust principal component analysis with complex noise. In ICML. 55--63. Qian Zhao Deyu Meng Zongben Xu Wangmeng Zuo and Lei Zhang. 2014. Robust principal component analysis with complex noise. In ICML. 55--63."},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273641"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1198\/106186006X113430"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2910585","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2910585","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:39:09Z","timestamp":1750221549000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2910585"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7,20]]},"references-count":49,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,2,28]]}},"alternative-id":["10.1145\/2910585"],"URL":"https:\/\/doi.org\/10.1145\/2910585","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7,20]]},"assertion":[{"value":"2015-06-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2016-03-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2016-07-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}