Abstract
We propose a fast population game dynamics, motivated by the analogy with infection and immunization processes within a population of ”players,” for finding dominant sets, a powerful graph-theoretical notion of a cluster. Each step of the proposed dynamics is shown to have a linear time/space complexity and we show that, under the assumption of symmetric affinities, the average population payoff is strictly increasing along any non-constant trajectory, thereby allowing us to prove that dominant sets are asymptotically stable (i.e., attractive) points for the proposed dynamics. The approach is general and can be applied to a large class of quadratic optimization problems arising in computer vision. Experimentally, the proposed dynamics is found to be orders of magnitude faster than and as accurate as standard algorithms.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Pavan, M., Pelillo, M.: Dominant sets and pairwise clustering. IEEE Trans. Pattern Anal. Machine Intell. 29(1), 167–172 (2007)
Neumann, J., von Cramon, D.Y., Forstmann, B.U., Zysset, S., Lohmann, G.: The parcellation of cortical areas using replicator dynamics in fMRI. NeuroImage 32(1), 208–219 (2006)
Wang, M., Ye, Z.L., Wang, Y., Wang, S.X.: Dominant sets clustering for image retrieval. Signal Process. 88(11), 2843–2849 (2008)
Hamid, R., Johnson, A., Batta, S., Bobick, A., Isbell, C., Coleman, G.: Detection and explanation of anomalous activities: representing activities as bags of event n-grams. In: CVPR, vol. 1, pp. 20–25 (2005)
Frommlet, F.: Tag SNP selection based on clustering according to dominant sets found using replicator dynamics. Adv. in Data Analysis (in press, 2010)
Wei, Q.D., Hu, W.M., Zhang, X.Q., Luo, G.: Dominant sets-based action recognition using image sequence matching. In: ICIP, vol. 6, pp. 133–136 (2007)
Albarelli, A., Torsello, A., Rota Bulò, S., Pelillo, M.: Matching as a non-cooperative game. In: ICCV (2009)
Todorovic, S., Ahuja, N.: Region-based hierarchical image matching. Int. J. Comput. Vision 78(1), 47–66 (2008)
Torsello, A., Rota Bulò, S., Pelillo, M.: Grouping with asymmetric affinities: a game-theoretic perspective. In: CVPR, pp. 292–299 (2006)
Weibull, J.W.: Evolutionary game theory. Cambridge University Press, Cambridge (1995)
Bomze, I.M., Pötscher, B.M.: Game Theoretical Foundations of Evolutionary Stability. Springer, Heidelberg (1989)
Bomze, I.M., Weibull, J.W.: Does neutral stability imply Lyapunov stability ? Games and Econ. Behaviour 11, 173–192 (1995)
Rota Bulò, S.: A game-theoretic framework for similarity-based data clustering. PhD thesis, University of Venice (2009)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In: ICCV, July 2001, vol. 2, pp. 416–423 (2001)
Pavan, M., Pelillo, M.: Efficient out-of-sample extension of dominant-set clusters. NIPS 17, 1057–1064 (2005)
Fowlkes, C., Belongie, S., Malik, F.C.J.: Spectral grouping using the Nyström method. IEEE Trans. Pattern Anal. Machine Intell. 26(2), 214–225 (2004)
Pardalos, P.M.: Quadratic problems defined on a convex hull of points. BIT Num. Math. 28(2), 323–329 (1988)
Bomze, I.M., Locatelli, M., Tardella, F.: Efficient and cheap bounds for (standard) quadratic optimization. Technical report, University ”La Sapienza” of Rome (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bulò, S.R., Bomze, I.M., Pelillo, M. (2010). Fast Population Game Dynamics for Dominant Sets and Other Quadratic Optimization Problems. In: Hancock, E.R., Wilson, R.C., Windeatt, T., Ulusoy, I., Escolano, F. (eds) Structural, Syntactic, and Statistical Pattern Recognition. SSPR /SPR 2010. Lecture Notes in Computer Science, vol 6218. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-14980-1_26
Download citation
DOI: https://doi.org/10.1007/978-3-642-14980-1_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-14979-5
Online ISBN: 978-3-642-14980-1
eBook Packages: Computer ScienceComputer Science (R0)