Loading...

Learning low-rank kernel matrices for constrained clustering

Baghshah, M. S ; Sharif University of Technology | 2011

546 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.neucom.2011.02.009
  3. Publisher: 2011
  4. Abstract:
  5. Constrained clustering methods (that usually use must-link and/or cannot-link constraints) have been received much attention in the last decade. Recently, kernel adaptation or kernel learning has been considered as a powerful approach for constrained clustering. However, these methods usually either allow only special forms of kernels or learn non-parametric kernel matrices and scale very poorly. Therefore, they either learn a metric that has low flexibility or are applicable only on small data sets due to their high computational complexity. In this paper, we propose a more efficient non-linear metric learning method that learns a low-rank kernel matrix from must-link and cannot-link constraints and the topological structure of data. We formulate the proposed method as a trace ratio optimization problem and learn appropriate distance metrics through finding optimal low-rank kernel matrices. We solve the proposed optimization problem much more efficiently than SDP solvers. Additionally, we show that the spectral clustering methods can be considered as a special form of low-rank kernel learning methods. Extensive experiments have demonstrated the superiority of the proposed method compared to recently introduced kernel learning methods
  6. Keywords:
  7. Constrained clustering ; Distance metric ; Kernel learning ; Low-rank kernel ; Semi-supervised ; Spectral ; Computational complexity ; Learning systems ; Optimization ; Matrix algebra ; Algorithm ; Artificial intelligence ; Cluster analysis ; Information processing ; Intermethod comparison ; Kernel method ; Learning ; Machine learning ; Mathematical computing ; Mathematics ; Nonlinear system ; Priority journal ; Problem solving ; Process optimization
  8. Source: Neurocomputing ; Volume 74, Issue 12-13 , 2011 , Pages 2201-2211 ; 09252312 (ISSN)
  9. URL: http://www.sciencedirect.com/science/article/pii/S0925231211001251