Semi-supervised graph regularized concept factorization with the class-driven constraint for image representation

Abstract

As a popular dimensionality reduction technique, concept factorization (CF) has been widely applied in image clustering. However, CF fails to extract the intrinsic structure of data space and does not utilize the label information. In this paper, a new semi-supervised graph regularized CF (SGCF) method is proposed, which makes full use of the limited label information and the graph regularization to improve the algorithm of clustering performance. Particularly, SGCF associates the class label information of data points with their new representations by using the class-driven constraint, and this constraint forces the new representations of data points to be more similar within the same class while different between classes. Furthermore, SGCF extracts the geometric structure of the data space by incorporating graph regularization. SGCF not only reveals the geometrical structure of the data space, but also takes into the limited label information account. We drive an efficient multiplicative update algorithm for SGCF to solve the optimization, and analyze the proposed SGCF method in terms of the convergence and computational complexity. Clustering experiments show the effectiveness of the SGCF method in comparison to other state-of-the-art methods.

Keywords

• concept factorization
• semi-supervised learning
• class-driven constraint
• label information