Abstract
We propose a new framework for the pairwise data clustering problem which is based on a “standard” quadratic program formulation, i.e., a continuous quadratic optimization problem with simplex (or probability) constraints. We then introduce a wide family of dynamic equations from evolutionary game theory, known as payoff-monotonic dynamics, and study their dynamical properties. These properties make any member of this family a potential heuristic for solving standard quadratic programs and, in particular, our data clustering problem. We demonstrate the potential of our framework for the problem of the unsupervised learning of shape categories from an image database. Experiments with two different similarity matrices (and databases) reported in the computer vision literature have been conducted, and the results confirm the effectiveness of our approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bhatia, N.P., Szegö, G.P.: Stability Theory of Dynamical Systems. Springer, Berlin (1970)
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. J. Wiley & Sons, New York (2001)
Fudenberg, D., Levine, D.K.: The Theory of Learning in Games. MIT Press, Cambridge (1998)
Hirsch, M.W., Smale, S.: Differential Equations, Dynamical Systems, and Linear Algebra. Academic Press, New York (1974)
Hofbauer, J.: Imitation dynamics for games. Collegium Budapest (1995) (preprint)
Hofbauer, J., Sigmund, K.: Evolutionary Games and Population Dynamics. Cambridge University Press, Cambridge (1998)
Hofmann, T., Buhmann, J.: Pairwise data clustering by deterministic annealing. IEEE Trans. Pattern Anal. Machine Intell. 19(1), 1–14 (1997)
Jain, A.K., Dubes, R.C.: Algorithms for Clustering Data. Prentice Hall, Englewood Cliffs (1988)
Klein, P.N., Sebastian, T.B., Kimia, B.B.: Shape matching using edit-distance: An implementation. In: Proc. 11th Ann. ACM-SIAM Symp. Discrete Algorithms (SODA), pp. 781–190 (2001)
Luo, B., Robles-Kelly, A., Torsello, A., Wilson, R.C., Hancock, E.R.: A probabilistic framework for graph clustering. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (2001)
Maynard Smith, J.: Evolution and the Theory of Games. Cambridge University Press, Cambridge (1982)
Motzkin, T.S., Straus, E.G.: Maxima for graphs and a new proof of a theorem of Turán. Canad. J. Math. 17, 533–540 (1965)
Pavan, M., Pelillo, M.: A new graph-theoretic approach to clustering and segmentation. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 145–152 (2003)
Pavan, M., Pelillo, M.: Dominant sets and hierarchical clustering. In: Proc. IEEE Int. Conf. Computer Vision (2003) (to appear)
Pelillo, M.: Replicator equations, maximal cliques, and graph isomorphism. Neural Computation 11(8), 2023–2045 (1999)
Pelillo, M.: Matching free trees, maximal cliques, and monotone game dynamics. IEEE Trans. Pattern Anal. Machine Intell. 24(11), 1535–1541 (2002)
Perona, P., Freeman, W.: A factorization approach to grouping. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 655–670. Springer, Heidelberg (1998)
Samuelson, L.: Evolutionary Games and Equilibrium Selection. MIT Press, Cambridge (1997)
Sarkar, S., Boyer, K.L.: Quantitative measures of change based on feature organization: Eigenvalues and eigenvectors. Computer Vision and Image Understanding 71(1), 110–136 (1998)
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Machine Intell. 22(8), 888–905 (2000)
Siddiqi, K., Shokoufaundeh, A., Dickinson, S.J., Zucker, S.W.: Shock graphs and shape matching. Int. J. Computer Vision 35(1) (1999)
Weibull, J.W.: Evolutionary Game Theory. MIT Press, Cambridge (1995)
Zucker, S.W., Dobbins, A., Iverson, L.: Two stages of curve detection suggest two styles of visual computation. Neural Computation 1, 68–81 (1989)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pavan, M., Pelillo, M. (2003). Pairwise Data Clustering Using Monotone Game Dynamics. In: Cappelli, A., Turini, F. (eds) AI*IA 2003: Advances in Artificial Intelligence. AI*IA 2003. Lecture Notes in Computer Science(), vol 2829. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39853-0_17
Download citation
DOI: https://doi.org/10.1007/978-3-540-39853-0_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20119-9
Online ISBN: 978-3-540-39853-0
eBook Packages: Springer Book Archive