Abstract
In this paper we propose a novel approach to obtain unambiguous and robust node attributes for matching non-attributed graphs. Such approach consists of exploiting the information coming from diffusion kernels to embed the subgraph induced by the neighborhood of each vertex in an Euclidean manifold and then use entropic graphs for measuring the α–entropy of the resulting distribution. Our experiments with random-generated graphs with 50 nodes show that at low edge densities, where the effect of structural noise is higher, this approach outperforms the description of the subgraph only in terms of diffusion kernels. Furthermore, our structural recognition experiments show that the approach has a practical application. All experiments were performed by weighting the well-known quadratic cost function used in the Softassign algorithm.
This is a preview of subscription content, log in via an institution to check access.
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
Bai, X., Hancock, E.: Heat kernels, manifolds and graph embedding. In: Fred, A. (ed.) SSPR&SPR 2004. LNCS, vol. 3138, pp. 198–206. Springer, Heidelberg (2004)
Bearwood, J., Halton, J.H., Hammersley, J.M.: The Shortest Path Through Many Points. Proc. Cambridge Philosophical Society 55, 299–327 (1959)
Belkin, M., Niyogi, P.: Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering. Neural Information Processing Systems 14, 634–640 (2002)
Bunke, H.: Recent Developments in Graph Matching. In: Proceedings of the International Conference on Pattern Recognition (ICPR 2000), vol. 2, pp. 2117–2124 (2000)
Bunke, H.: Error Correcting Graph Matching: On the Influence of the Underlying Cost Function. IEEE Transactions on Pattern Analysis and Machine Intelligence 21(9), 917–922 (1999)
Costa, J., Hero, A.O.: Geodesic Entropic Graphs for Dimension and Entropy Estimation in Manifold Learning. IEEE Transactions on Signal Processing 52(8), 2210–2221 (2004)
Chung, F.R.K.: Spectral Graph Theory. In: Conference Board of the Mathematical Sciences (CBMS), vol. 92. American Mathematical Society, Providence (1997)
Finch, A.M., Wilson, R.C., Hancock, E.: An Energy Function and Continuous Edit Process for Graph Matching. Neural Computation 10(7), 1873–1894 (1998)
Gold, S., Rangarajan, A.: A Graduated Assignment Algorithm for Graph Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence 18(4), 377–388 (1996)
Hero, A.O., Ma, B., Michel, O., Gorman, J.D.: Applications of Entropic Spanning Graphs. IEEE Signal Processing Magazine 19(5), 85 (2002)
Jiang, X., Münger, A., Bunke, H.: On Median Graphs: Properties, Algorithms, and Applications. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(10), 1144–1151 (2001)
Kondor, R.I., Lafferty, J.: Diffusion Kernels on Graphs and other Discrete Input Spaces. In: Sammut, C., et al. (eds.) ICML 2002, pp. 315–322. Morgan Kaufmann, San Francisco (2002)
Lafferty, J., Lebanon, G.: Diffusion Kernels on Statistical Manifolds. CMU Technical Report CMU-04-101 (2004)
Lozano, M.A., Escolano, F.: EM Algorithm for Clustering an Ensemble of Graphs with Comb Matching. In: Rangarajan, A., Figueiredo, M.A.T., Zerubia, J. (eds.) EMMCVPR 2003. LNCS, vol. 2683, pp. 52–67. Springer, Heidelberg (2003)
Lozano, M.A., Escolano, F.: A significant improvement of softassign with diffusion kernels. In: Fred, A., et al. (eds.) SSPR&SPR 2004. LNCS, vol. 3138, pp. 76–84. Springer, Heidelberg (2004)
Lozano, M.A., Escolano, F.: Regularization kernels and softassign. In: Sanfeliu, A., et al. (eds.) CIARP 2004. LNCS, vol. 3287, pp. 321–328. Springer, Heidelberg (2004)
Lozano, M.A., Escolano, F.: Structural recognition with kernelized softassign. In: Lemaître, C., et al. (eds.) IBERAMIA 2004. LNCS, vol. 3315, pp. 626–635. Springer, Heidelberg (2004)
Luo, B., Hancock, E.R.: Structural Graph Matching Using the EM Algorithm and Singular Value Decomposition. IEEE Trans. on Pattern Analysis and Machine Intelligence 23(10), 1120–1136 (2001)
Luo, B., Wilson, R.C., Hancock, E.R.: A spectral approach to learning structural variations in graphs. In: Crowley, J.L., et al. (eds.) ICVS 2003. LNCS, vol. 2626, pp. 407–417. Springer, Heidelberg (2003)
Pelillo, M.: Replicator Equations, Maximal Cliques, and Graph Isomorphism. Neural Computation 11, 1933–1955 (1999)
Rényi, A.: On Measures of Entropy and Information. In: Proc. 4th Berkeley Symp. Math. Stat. and Prob., vol. 1, pp. 547–561 (1961)
Robles-Kelly, A., Hancock, E.R.: Graph Matching Using Spectral Seriation. In: Rangarajan, A., et al. (eds.) EMMCVPR 2003. LNCS, vol. 2683, pp. 517–532. Springer, Heidelberg (2003)
Sanfeliu, A., Fu, K.S.: A Distance Measure Between Attributed Relational Graphs for Pattern Recognition. IEEE Transactions on Systems, Man, and Cybernetics 13, 353–362 (1983)
Serratosa, F., Alquézar, R., Sanfeliu, A.: Function-described graphs for modelling objects represented by sets of attributed graphs. Pattern Recognition 23(3), 781–798 (2003)
Smola, A., Kondor, R.I.: Kernels and regularization on graphs. In: Schölkopf, et al. (eds.) COLT/Kernel 2003. LNCS, vol. 2777, pp. 144–158. Springer, Heidelberg (2003)
Wilson, R.C., Hancock, E.R.: Structual Matching by Discrete Relaxation. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(6), 634–648 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lozano, M.A., Escolano, F. (2005). Local Entropic Graphs for Globally-Consistent Graph Matching. In: Brun, L., Vento, M. (eds) Graph-Based Representations in Pattern Recognition. GbRPR 2005. Lecture Notes in Computer Science, vol 3434. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-31988-7_33
Download citation
DOI: https://doi.org/10.1007/978-3-540-31988-7_33
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25270-2
Online ISBN: 978-3-540-31988-7
eBook Packages: Computer ScienceComputer Science (R0)