ℓ2,1 Norm and Hessian Regularized Non-Negative Matrix Factorization with Discriminability for Data Representation
Source abstract
Abstract
Matrix factorization based methods have widely been used in data representation. Among them, Non-negative Matrix Factorization (NMF) is a promising technique owing to its psychological and physiological interpretation of spontaneously occurring data. On one hand, although traditional Laplacian regularization can enhance the performance of NMF, it still suffers from the problem of its weak extrapolating ability. On the other hand, standard NMF disregards the discriminative information hidden in the data and cannot guarantee the sparsity of the factor matrices. In this paper, a novel algorithm called ℓ 2 , 1 norm and Hessian Regularized Non-negative Matrix Factorization with Discriminability (ℓ 2 , 1 HNMFD), is developed to overcome the aforementioned problems. In ℓ 2 , 1 HNMFD, Hessian regularization is introduced in the framework of NMF to capture the intrinsic manifold structure of the data. ℓ 2 , 1 norm constraints and approximation orthogonal constraints are added to assure the group sparsity of encoding matrix and characterize the discriminative information of the data simultaneously. To solve the objective function, an efficient optimization scheme is developed to settle it. Our experimental results on five benchmark data sets have demonstrated that ℓ 2 , 1 HNMFD can learn better data representation and provide better clustering results.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Face and Expression Recognition · Remote-Sensing Image Classification · Image Retrieval and Classification Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information and Technology, Northwest University of China, Xi’an 710127, China
Department of Computer Science, University of North Carolina at Charlotte, Charlotte, NC 28223, USA
References (28)
Show source-provided references
1. Verleysen, M., and François, D. (2005, January 8–10). The Curse of Dimensionality in Data Mining and Time Series Prediction. Proceedings of the Computational Intelligence and Bioinspired Systems, Barcelona, Spain.10.1007/11494669_93 ↗
2. Principal component analysis10.1002/wics.101 ↗
3. Learning the parts of objects by non-negative matrix factorization10.1038/44565 ↗
4. Guillamet, D., and Vitria, J. (2002, January 24–25). Classifying faces with nonnegative matrix factorization. Proceedings of the 5th Catalan Conference for Artificial Intelligence, Castellón, Spain.
5. Nonlinear non-negative component analysis algorithms10.1109/TIP.2009.2038816 ↗
6. Xu, W., Liu, X., and Gong, Y. (August, January 28). Document clustering based on non-negative matrix factorization. Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval, Toronto, ON, Canada.
7. Graph regularized nonnegative matrix factorization for data representation10.1109/TPAMI.2010.231 ↗
8. Manifold regularized sparse NMF for hyperspectral unmixing10.1109/TGRS.2012.2213825 ↗
9. Gu, Q., and Zhou, J. (2009, January 7–10). Neighborhood Preserving Nonnegative Matrix Factorization. Proceedings of the British Machine Vision Conference, London, UK.10.5244/C.23.9 ↗
10. Kim, K.I., Steinke, F., and Hein, M. (2009, January 7–10). Semi-supervised regression using Hessian energy with an application to semi-supervised dimensionality reduction. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada.
11. Non-negative matrix factorization with sparseness constraints
12. Cai, D., He, X., and Han, J. (2007, January 28–31). Spectral regression: A unified approach for sparse subspace learning. Proceedings of the Seventh IEEE International Conference on Data Mining (ICDM 2007), Omaha, NE, USA.10.1109/ICDM.2007.89 ↗
13. The F∞-norm support vector machine
14. Nie, F., Huang, H., Cai, X., and Ding, C.H. (2010, January 6–9). Efficient and robust feature selection via joint ℓ2,1-norms minimization. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada.
15. Yang, Y., Shen, H.T., Ma, Z., Huang, Z., and Zhou, X. (2011, January 16–22). ℓ2,1-norm regularized discriminative feature selection for unsupervised learning. Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI11), Barcelona, Spain.
16. Gu, Q., Li, Z., and Han, J. (2011, January 16–22). Joint feature selection and subspace learning. Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI11), Barcelona, Spain.
17. L1/2 regularization: A thresholding representation theory and a fast solver10.1109/TNNLS.2012.2197412 ↗
18. Hyperspectral unmixing via L1/2 sparsity-constrained nonnegative matrix factorization10.1109/TGRS.2011.2144605 ↗
19. Adaptive L1/2 Sparsity-Constrained NMF With Half-Thresholding Algorithm for Hyperspectral Unmixing10.1109/JSTARS.2015.2401603 ↗
20. Distributed Blind Hyperspectral Unmixing via Joint Sparsity and Low-Rank Constrained Non-Negative Matrix Factorization10.1109/TCI.2017.2693967 ↗
21. Li, X., Cui, G., and Dong, Y. (2016). Graph regularized non-negative low-rank matrix factorization for image clustering. IEEE Trans. Cybern., 1–14.
22. Liu, H., and Wu, Z. (2010, January 11–15). Non-negative matrix factorization with constraints. Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence, Atlanta, Georgia.
23. Li, Z., Tang, J., and He, X. (2017). Robust Structured Nonnegative Matrix Factorization for Image Representation. IEEE Trans. Neural Netw. Learn. Syst., 1–14.
24. Lee, D.D., and Seung, H.S. (December, January 27). Algorithms for non-negative matrix factorization. Proceedings of the Advances in Neural Information Processing Systems 13 (NIPS 2000), Denver, CO, USA.
25. Steinke, F., and Hein, M. (2008, January 8–10). Non-parametric regression between manifolds. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada.
26. Ye, J., Zhao, Z., and Wu, M. (2008, January 8–10). Discriminative k-means for clustering. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada.
27. Image clustering using local discriminant models and global integration10.1109/TIP.2010.2049235 ↗
28. Normalized cuts and image segmentation10.1109/34.868688 ↗