Robust sparse coding for one-class classification based on correntropy and logarithmic penalty function. (March 2021)

• Record Type: Journal Article
• Authors: Xing, Hong-Jie; Liu, Ya-Jie; He, Zi-Chuan
• Is Part Of: Pattern recognition. Volume 111(2021)
• Publication Date: 2021-03
• Subjects: Sparse coding -- One-class classification -- Logarithmic penalty function -- Correntropy -- One-class support vector machine; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107685
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Robust sparse coding for one-class classification based on correntropy and logarithmic penalty function is proposed. The optimization problem of the proposed robust sparse coding is iteratively solved by the half-quadratic optimization technique. The generalization performance of robust sparse coding is analyzed from the theoretical analysis. The effectiveness of the proposed method is validated on twenty UCI benchmark data sets and one handwritten digit data set. Abstract: Similar to binary and multi-class classifiers, one-class classifiers have to face the difficulty of 'curse of dimensionality' when they are applied to deal with high-dimensional samples. As an efficient dimensionality reduction method, sparse coding tries to learn a set of over-complete bases to represent the given samples. It can effectively overcome the 'curse of dimensionality' problem. However, the traditional sparse coding only fit for tackling Gaussian noise. When the noise within the given set of samples obey non-Gaussian distribution, the conventional sparse coding cannot obtain accurate coefficient vectors. To make sparse coding more fit for dealing with non-Gaussian noise and enhance the sparseness of the obtained coefficient vectors, correntropy is utilized to substitute its reconstruction error term and logarithmic penalty function is introduced as its regularization term. Furthermore, the obtained sparse coefficient vectors are used as the input vectors for one-class support vector machine (OCSVM). Experimental results on twenty UCI benchmark data sets and one handwritten digit data set demonstrate that the proposed method achieves better anti-noise and generalization abilities in comparison with its related approaches.