Clustering Large Graphs via the Singular Value Decomposition

  • Authors:

  • P. Drineas;A. Frieze;R. Kannan;S. Vempala;V. Vinay

  • Affiliations:

  • Computer Science Department, Rensselaer Polytechnic Institute, Troy, NY 12180. drinep@cs.rpi.edu;Department of Mathematical Sciences, Carnegie Mellon University, Pittsburgh, PA 15213. alan@random.math.cmu.edu;Computer Science Department, Yale University, New Haven, CT 06520. kannan@cs.yale.edu;Department of Mathematics, M.I.T., Cambridge, MA 02139. vempala@math.mit.edu;Indian Institute of Science, Bangalore, India. vinay@csa.iisc.ernet.in

  • Venue:
  • Machine Learning
  • Year:
  • 2004

Quantified Score

Hi-index 0.06

Visualization

Abstract

We consider the problem of partitioning a set of m points in the n-dimensional Euclidean space into k clusters (usually m and n are variable, while k is fixed), so as to minimize the sum of squared distances between each point and its cluster center. This formulation is usually the objective of the k-means clustering algorithm (Kanungo et al. (2000)). We prove that this problem in NP-hard even for k = 2, and we consider a continuous relaxation of this discrete problem: find the k-dimensional subspace V that minimizes the sum of squared distances to V of the m points. This relaxation can be solved by computing the Singular Value Decomposition (SVD) of the m × n matrix A that represents the m points; this solution can be used to get a 2-approximation algorithm for the original problem. We then argue that in fact the relaxation provides a generalized clustering which is useful in its own right.Finally, we show that the SVD of a random submatrix—chosen according to a suitable probability distribution—of a given matrix provides an approximation to the SVD of the whole matrix, thus yielding a very fast randomized algorithm. We expect this algorithm to be the main contribution of this paper, since it can be applied to problems of very large size which typically arise in modern applications.