Structure Preserving Sparse Coding for Data Representation

Sparse coding methods have shown the superiority in data representation. However, traditional sparse coding methods cannot explore the manifold structure embedded in data. To alleviate this problem, a novel method, called Structure Preserving Sparse Coding (SPSC), is proposed for data representation. SPSC imposes both local affinity and distant repulsion constraints on the model of sparse coding. Therefore, the proposed SPSC method can effectively exploit the structure information of high dimensional data. Beside, an efficient optimization scheme for our proposed SPSC method is developed, and the convergence analysis on three datasets are presented. Extensive experiments on several benchmark datasets have shown the superior performance of our proposed method compared with other state-of-the-art methods.