Robust Semisupervised Nonnegative Local Coordinate Factorization for Data Representation
Obtaining an optimum data representation is a challenging issue that arises in many intellectual data processing techniques such as data mining, pattern recognition, and gene clustering. Many existing methods formulate this problem as a nonnegative matrix factorization (NMF) approximation problem. T...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2018-01-01
|
| Series: | Complexity |
| Online Access: | http://dx.doi.org/10.1155/2018/7963210 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849307514587316224 |
|---|---|
| author | Wei Jiang Qian Lv Chenggang Yan Kewei Tang Jie Zhang |
| author_facet | Wei Jiang Qian Lv Chenggang Yan Kewei Tang Jie Zhang |
| author_sort | Wei Jiang |
| collection | DOAJ |
| description | Obtaining an optimum data representation is a challenging issue that arises in many intellectual data processing techniques such as data mining, pattern recognition, and gene clustering. Many existing methods formulate this problem as a nonnegative matrix factorization (NMF) approximation problem. The standard NMF uses the least square loss function, which is not robust to outlier points and noises and fails to utilize prior label information to enhance the discriminability of representations. In this study, we develop a novel matrix factorization method called robust semisupervised nonnegative local coordinate factorization by integrating robust NMF, a robust local coordinate constraint, and local spline regression into a unified framework. We use the l2,1 norm for the loss function of the NMF and a local coordinate constraint term to make our method insensitive to outlier points and noises. In addition, we exploit the local and global consistencies of sample labels to guarantee that data representation is compact and discriminative. An efficient multiplicative updating algorithm is deduced to solve the novel loss function, followed by a strict proof of the convergence. Several experiments conducted in this study on face and gene datasets clearly indicate that the proposed method is more effective and robust compared to the state-of-the-art methods. |
| format | Article |
| id | doaj-art-2aec8a72e00b4ee1b1062bf2a92e1a82 |
| institution | Kabale University |
| issn | 1076-2787 1099-0526 |
| language | English |
| publishDate | 2018-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Complexity |
| spelling | doaj-art-2aec8a72e00b4ee1b1062bf2a92e1a822025-08-20T03:54:43ZengWileyComplexity1076-27871099-05262018-01-01201810.1155/2018/79632107963210Robust Semisupervised Nonnegative Local Coordinate Factorization for Data RepresentationWei Jiang0Qian Lv1Chenggang Yan2Kewei Tang3Jie Zhang4School of Mathematics, Liaoning Normal University, Dalian 116029, ChinaSchool of Mathematics, Liaoning Normal University, Dalian 116029, ChinaInstitute of Information and Control, Hangzhou Dianzi University, Hangzhou 541004, ChinaSchool of Mathematics, Liaoning Normal University, Dalian 116029, ChinaSchool of Mathematics, Liaoning Normal University, Dalian 116029, ChinaObtaining an optimum data representation is a challenging issue that arises in many intellectual data processing techniques such as data mining, pattern recognition, and gene clustering. Many existing methods formulate this problem as a nonnegative matrix factorization (NMF) approximation problem. The standard NMF uses the least square loss function, which is not robust to outlier points and noises and fails to utilize prior label information to enhance the discriminability of representations. In this study, we develop a novel matrix factorization method called robust semisupervised nonnegative local coordinate factorization by integrating robust NMF, a robust local coordinate constraint, and local spline regression into a unified framework. We use the l2,1 norm for the loss function of the NMF and a local coordinate constraint term to make our method insensitive to outlier points and noises. In addition, we exploit the local and global consistencies of sample labels to guarantee that data representation is compact and discriminative. An efficient multiplicative updating algorithm is deduced to solve the novel loss function, followed by a strict proof of the convergence. Several experiments conducted in this study on face and gene datasets clearly indicate that the proposed method is more effective and robust compared to the state-of-the-art methods.http://dx.doi.org/10.1155/2018/7963210 |
| spellingShingle | Wei Jiang Qian Lv Chenggang Yan Kewei Tang Jie Zhang Robust Semisupervised Nonnegative Local Coordinate Factorization for Data Representation Complexity |
| title | Robust Semisupervised Nonnegative Local Coordinate Factorization for Data Representation |
| title_full | Robust Semisupervised Nonnegative Local Coordinate Factorization for Data Representation |
| title_fullStr | Robust Semisupervised Nonnegative Local Coordinate Factorization for Data Representation |
| title_full_unstemmed | Robust Semisupervised Nonnegative Local Coordinate Factorization for Data Representation |
| title_short | Robust Semisupervised Nonnegative Local Coordinate Factorization for Data Representation |
| title_sort | robust semisupervised nonnegative local coordinate factorization for data representation |
| url | http://dx.doi.org/10.1155/2018/7963210 |
| work_keys_str_mv | AT weijiang robustsemisupervisednonnegativelocalcoordinatefactorizationfordatarepresentation AT qianlv robustsemisupervisednonnegativelocalcoordinatefactorizationfordatarepresentation AT chenggangyan robustsemisupervisednonnegativelocalcoordinatefactorizationfordatarepresentation AT keweitang robustsemisupervisednonnegativelocalcoordinatefactorizationfordatarepresentation AT jiezhang robustsemisupervisednonnegativelocalcoordinatefactorizationfordatarepresentation |