Minh Thuy Ta, Hoai An Le Thi, Lydia Boudjeloud-Assala: "An Efficient Clustering Method for Massive Dataset Based on DC Programming and DCA Approach".

Abstract: In this paper, we study an efficient nonconvex optimization method for clustering on massive datasets. Our approach consists of two phases and is based on DC (Difference of Convex functions) programming and DCA (DC Algorithms). In the first phase, the data is divided into subsets on which an efficient DCA for clustering is investigated. In the second phase, another DCA for weighted clustering on the set of centers obtained by phase 1 is presented. The numerical results on real datasets show the efficiency of our method.

 

Keywords: Clustering, Data stream, Massive dataset, DCA, DCA Weight.

 

Citation: Minh Thuy Ta, Hoai An Le Thi, Lydia Boudjeloud-Assala: An Efficient Clustering Method for Massive Dataset Based on DC Programming and DCA Approach. Neural Information Processing, Lecture Notes in Computer Science, volume 8227, pp 538-545, 2013.

 

Download link