Unsupervised embedded feature learning for deep clustering with stacked sparse auto-encoder. (30th December 2021)

• Record Type: Journal Article
• Authors: Cai, Jinyu; Wang, Shiping; Guo, Wenzhong
• Is Part Of: Expert systems with applications. Volume 186(2021)
• Publication Date: 2021-12-30
• Subjects: Machine learning -- Deep clustering -- Feature representation -- Auto-encoder -- Neural networks; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2021.115729
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: Deep clustering attempts to capture the feature representation that benefits the clustering issue. Although the existing deep clustering methods have achieved encouraging performance in many research fields, there still present some shortcomings, such as the lack of consideration of local structure retention and sparse characteristics of input data. To this end, we propose a deep stacked sparse embedded clustering method in this paper, which considers both the local structure preservation and sparse property of inputs. The proposed method is trained to capture the feature representation for an input data by the guidance of the clustering and reconstruction loss, where the reconstruction loss prevents the corruption of feature space and preserve the local structure. Besides, sparse constraint is added to the encoder to avoid learning of unimportant features. Through simultaneously minimizing the reconstruction and clustering loss, the proposed method is able to jointly learn the clustering oriented features and optimize the assignment of cluster labels. Then we conduct amounts of comparative experiments, which consists of seven clustering methods and six publicly available image data sets. Eventually, comprehensive experiments validate the effectiveness of introducing sparse property and preserving local structure in the proposed method. Highlights: Propose a new deep clustering method by introducing sparse embedded learning. Learn an effective embedded representation in the hidden layer. Improved the local structure retention strategy by exploiting the sparse constraint. Present a joint optimization framework for feature learning and data clustering.