Affiliations: [a] Computer Engineering Department, Sharif University of Technology, Tehran, Iran | [b] Electrical Engineering Department, Sharif University of Technology, Tehran, Iran
Correspondence:
[*]
Corresponding author: M. Soleymani Baghshah, PhD Candidate, Department of Computer Engineering, Sharif University of Technology (SUT), Azadi St., Tehran, Iran. PO Box: 1458889694. Tel.: +98 21 6616 4102; Fax: +98 21 6601 9246; E-mail: soleyman@ce.sharif.edu.
Abstract: Metric learning is a powerful approach for semi-supervised clustering. In this paper, a metric learning method considering both pairwise constraints and the geometrical structure of data is introduced for semi-supervised clustering. At first, a smooth metric is found (based on an optimization problem) using positive constraints as supervisory information. Then, an extension of this method employing both positive and negative constraints is introduced. As opposed to the existing methods, the extended method has the capability of considering both positive and negative constraints while considering the topological structure of data. The proposed metric learning method can improve performance of semi-supervised clustering algorithms. Experimental results on real-world data sets show the effectiveness of this method.
