Graph regularized-based semi-supervised non-negative matrix factorization

Computer Engineering and Applications ›› 2012, Vol. 48 ›› Issue (36): 194-200.

Previous Articles Next Articles

Graph regularized-based semi-supervised non-negative matrix factorization

DU Shiqiang1, SHI Yuqing2, WANG Weilan1, MA Ming1

1.School of Mathematics and Computer Science, Northwest University for Nationalities, Lanzhou 730030, China
2.School of Electrical Engineering, Northwest University for Nationalities, Lanzhou 730030, China

Online:2012-12-21 Published:2012-12-21

基于图正则化的半监督非负矩阵分解

杜世强1，石玉清2，王维兰1，马明1

1.西北民族大学数学与计算机科学学院，兰州 730030
2.西北民族大学电气工程学院，兰州 730030

Abstract

Abstract: This paper presents a novel algorithm called Graph regularized-based Semi-supervised NMF（GSNMF）. It overcomes the shortcomings which ignore the geometric structure and the label information of the data for Non-negative Matrix Factorization（NMF）, Constrained NMF（CNMF） and Graphed regularized NMF（GNMF）. Moreover, those algorithms are special case of GSNMF. The convergence proof of this algorithm is provided. GSNMF preserves the intrinsic geometry of data and uses the label information as semi-supervised learning. It makes nearby samples with the same class-label more compact, and nearby classes separated. Compared with NMF, LNMF, PNMF, GNMF and CNMF, experiment results on ORL face database, FERET face database and USPS handwrite database have shown that the proposed method achieves better clustering results.

Key words: image clustering, semi-supervised learning, Non-negative Matrix Factorization（NMF）, graph regularized

摘要： 提出了一种基于图正则化的半监督非负矩阵分解算法（GSNMF），克服了非负矩阵分解（NMF）、约束非负矩阵分解（CNMF）和图正则化非负矩阵分解（GNMF）方法忽略样本数据的局部几何结构或标签信息不足的缺陷，且NMF、CNMF和GNMF均为GSNMF的特例。也从理论上证明了GSNMF算法的收敛性。该算法对样本数据进行低维非负分解时，在图框架下既保持数据的几何结构，又利用已知样本的标签信息，在进行半监督学习时，同类样本能更好地聚集而类间距离尽可能大。在人脸数据库ORL、FERET和手写体数据库USPS上的仿真结果表明，相对于NMF及其一些改进算法，GSNMF均具有更高的聚类精度。

关键词: 图像聚类, 半监督学习, 非负矩阵分解, 图正则化

DU Shiqiang1, SHI Yuqing2, WANG Weilan1, MA Ming1. Graph regularized-based semi-supervised non-negative matrix factorization[J]. Computer Engineering and Applications, 2012, 48(36): 194-200.

杜世强1，石玉清2，王维兰1，马明1. 基于图正则化的半监督非负矩阵分解[J]. 计算机工程与应用, 2012, 48(36): 194-200.

[1]	ZOU Chengming, HU Youpu. Monocular Depth Estimation in Outdoor Scene with Generative Adversarial Network [J]. Computer Engineering and Applications, 2021, 57(6): 176-183.
[2]	MI Yuan, TANG Hengliang. Rumor Identification Research Based on Graph Convolutional Network [J]. Computer Engineering and Applications, 2021, 57(13): 161-167.
[3]	TANG Huanling, LIU Yanhong, ZHENG Han, DOU Quansheng, LU Mingyu. Imbalanced Text Categorization Method with SLDA Topic Model [J]. Computer Engineering and Applications, 2021, 57(12): 144-154.
[4]	SONG Lili, LI Bin, ZHAO Junya, LIU Guofeng. Normality Resampling of Improved Metric Learning Method for Person Re-Identification [J]. Computer Engineering and Applications, 2020, 56(8): 158-165.
[5]	HAN Song, HAN Qiuhong. Review of Semi-Supervised Learning Research [J]. Computer Engineering and Applications, 2020, 56(6): 19-27.
[6]	SUI Xiuwu, NIU Jiabao, LI Haotian, QIAO Mingmin. Upper Limb sEMG Gesture Recognition Method Based on NMF-SVM Model [J]. Computer Engineering and Applications, 2020, 56(17): 161-166.
[7]	LUO Can, LI Xuehua. Light Field Depth Estimation Algorithm for Multi-occlusion Interference Handling [J]. Computer Engineering and Applications, 2020, 56(12): 193-200.
[8]	YANG Shuo, LIU Bing, ZHOU Yong. Semi-Supervised Low-Rank Kernel Learning Algorithm Based on Sparse Coding [J]. Computer Engineering and Applications, 2019, 55(7): 175-181.
[9]	ZHANG Pu1, CHAI Bianfang1, ZHANG Jing1, LI Wenbin2. Semi-Supervised Representation Learning Method for Attributed Networks [J]. Computer Engineering and Applications, 2019, 55(12): 117-123.
[10]	WANG Yuye, CHEN Jianmei. Safe semi-supervised collaborative filtering recommendation algorithm [J]. Computer Engineering and Applications, 2018, 54(8): 107-111.
[11]	WU Mingsheng, DENG Xiaogang. Semi supervised pattern classification method based on Tri-DE-ELM [J]. Computer Engineering and Applications, 2018, 54(3): 109-114.
[12]	LU Yueming1, WANG Liang1, QIU Agen1, ZHANG Yongchuan1，2, ZHAO Yangyang1. Kriging interpolation method based on semi-supervised learning [J]. Computer Engineering and Applications, 2018, 54(22): 265-270.
[13]	CHEN Yuqi1, LEI Gang1, YAO Minghai2, YI Yugen1. Locality constrained adaptive graph based label propagation approach [J]. Computer Engineering and Applications, 2018, 54(20): 14-19.
[14]	LI Cunhe, ZHU Hongbo. MIML algorithm E-MIMLSVM+ based on semi-supervised learning [J]. Computer Engineering and Applications, 2018, 54(2): 149-154.
[15]	CHEN Juan1, ZHU Fuxi1，2. Time series classification based on PU problem with semi-supervised learning and active learning [J]. Computer Engineering and Applications, 2018, 54(11): 116-121.

Graph regularized-based semi-supervised non-negative matrix factorization

基于图正则化的半监督非负矩阵分解

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics