Semi-supervised metric learning by maximizing constraint margin Conference

Wang, F, Chen, S, Zhang, C et al. (2008). Semi-supervised metric learning by maximizing constraint margin . 1457-1458. 10.1145/1458082.1458331

cited authors

  • Wang, F; Chen, S; Zhang, C; Li, T

fiu authors

abstract

  • Distance metric learning is an old problem that has been researched in the supervised learning field for a very long time. In this paper, we consider the problem of learning a proper distance metric under the guidance of some weak supervisory information. Specifically, those information are in the form of pairwise constraints which specify whether a pair of data points are in the same class(must link constraints) or in the different classes(cannot link constraints). Given those constraints, our algorithm aims to learn a distance metric under which the points with must link constraints are pushed as close as possible, while simultaneously the points with cannot link constraints are pulled away as far as possible. Finally the experimental results are presented to show the effectiveness of our method.

publication date

  • December 1, 2008

Digital Object Identifier (DOI)

International Standard Book Number (ISBN) 13

  • 9781595939913

start page

  • 1457

end page

  • 1458