Advertisement

Generalized Median Graph via Iterative Alternate Minimizations

  • Nicolas BoriaEmail author
  • Sébastien Bougleux
  • Benoit Gaüzère
  • Luc Brun
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11510)

Abstract

Computing a graph prototype may constitute a core element for clustering or classification tasks. However, its computation is an NP-Hard problem, even for simple classes of graphs. In this paper, we propose an efficient approach based on block coordinate descent to compute a generalized median graph from a set of graphs. This approach relies on a clear definition of the optimization process and handles labeling on both edges and nodes. This iterative process optimizes the edit operations to perform on a graph alternatively on nodes and edges. Several experiments on different datasets show the efficiency of our approach.

Keywords

Median graph Graph Edit Distance Optimization 

Notes

Acknowledgments

This work is supported by Région Normandie through RIN AGAC project.

References

  1. 1.
    Bougleux, S., Gaüzère, B., Brun, L.: Graph edit distance as a quadratic program. In: International Conference on Pattern Recognition, pp. 1701–1706 (2016).  https://doi.org/10.1109/ICPR.2016.7899881
  2. 2.
    Bunke, H., Allermann, G.: Inexact graph matching for structural pattern recognition. Pattern Recogn. Lett. 1(4), 245–253 (1983).  https://doi.org/10.1016/0167-8655(83)90033-8CrossRefzbMATHGoogle Scholar
  3. 3.
    Chaieb, R., Kalti, K., Luqman, M.M., Coustaty, M., Ogier, J.M., Amara, N.E.B.: Fuzzy generalized median graphs computation: application to content-based document retrieval. Pattern Recogn. 72, 266–284 (2017).  https://doi.org/10.1016/j.patcog.2017.07.030CrossRefGoogle Scholar
  4. 4.
    Daller, É., Bougleux, S., Gaüzère, B., Brun, L.: Approximate graph edit distance by several local searches in parallel. In: International Conference on Pattern Recognition Applications and Methods, pp. 149–158 (2018).  https://doi.org/10.5220/0006599901490158
  5. 5.
    Ferrer, M.: Theory and algorithms on the median graph. Application to graph-based classification and clustering. Ph.D. thesis, Universitat Autònoma de Barcelona (2008). http://hdl.handle.net/10803/5788
  6. 6.
    Ferrer, M., Bardají, I., Valveny, E., Karatzas, D., Bunke, H.: Median graph computation by means of graph embedding into vector spaces. In: Fu, Y., Ma, Y. (eds.) Graph Embedding for Pattern Analysis, pp. 45–71. Springer, New York (2013).  https://doi.org/10.1007/978-1-4614-4457-2_3CrossRefGoogle Scholar
  7. 7.
    Ferrer, M., Karatzas, D., Valveny, E., Bardaji, I., Bunke, H.: A generic framework for median graph computation based on a recursive embedding approach. Comput. Vis. Image Underst. 115(7), 919–928 (2011).  https://doi.org/10.1016/j.cviu.2010.12.010CrossRefGoogle Scholar
  8. 8.
    Ferrer, M., Valveny, E., Serratosa, F., Riesen, K., Bunke, H.: Generalized median graph computation by means of graph embedding in vector spaces. Pattern Recogn. 43(4), 1642–1655 (2010).  https://doi.org/10.1016/j.patcog.2009.10.013CrossRefzbMATHGoogle Scholar
  9. 9.
    Hlaoui, A., Wang, S.: Median graph computation for graph clustering. Soft Comput. 10(1), 47–53 (2006).  https://doi.org/10.1007/s00500-005-0464-1CrossRefGoogle Scholar
  10. 10.
    Jiang, X., Munger, A., Bunke, H.: On median graphs: properties, algorithms, and applications. IEEE Trans. Pattern Anal. Mach. Intell. 23(10), 1144–1151 (2001).  https://doi.org/10.1109/34.954604CrossRefGoogle Scholar
  11. 11.
    Moreno-García, C.F., Serratosa, F., Jiang, X.: Correspondence edit distance to obtain a set of weighted means of graph correspondences. Pattern Recogn. Lett. (2018).  https://doi.org/10.1016/j.patrec.2018.08.027CrossRefGoogle Scholar
  12. 12.
    Mukherjee, L., Singh, V., Peng, J., Xu, J., Zeitz, M.J., Berezney, R.: Generalized median graphs and applications. J. Comb. Optim. 17(1), 21–44 (2009).  https://doi.org/10.1007/s10878-008-9184-7CrossRefMathSciNetzbMATHGoogle Scholar
  13. 13.
    Musmanno, L.M., Ribeiro, C.C.: Heuristics for the generalized median graph problem. Eur. J. Oper. Res. 254(2), 371–384 (2016).  https://doi.org/10.1016/j.ejor.2016.03.048CrossRefMathSciNetzbMATHGoogle Scholar
  14. 14.
    Nienkötter, A., Jiang, X.: Improved prototype embedding based generalized median computation by means of refined reconstruction methods. In: Robles-Kelly, A., Loog, M., Biggio, B., Escolano, F., Wilson, R. (eds.) S+SSPR 2016. LNCS, vol. 10029, pp. 107–117. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-49055-7_10CrossRefGoogle Scholar
  15. 15.
    Rebagliati, N., Solé-Ribalta, A., Pelillo, M., Serratosa, F.: On the relation between the common labelling and the median graph. In: Gimel’farb, G., et al. (eds.) SSPR /SPR 2012. LNCS, vol. 7626, pp. 107–115. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-34166-3_12CrossRefGoogle Scholar
  16. 16.
    Riesen, K.: Structural Pattern Recognition with Graph Edit Distance. ACVPR. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-27252-8CrossRefzbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Nicolas Boria
    • 1
    Email author
  • Sébastien Bougleux
    • 1
  • Benoit Gaüzère
    • 2
  • Luc Brun
    • 1
  1. 1.Normandie Univ, UNICAEN, ENSICAEN, CNRS, GREYCCaenFrance
  2. 2.Normandie Univ, INSA ROUEN Normandie, LITISRouenFrance

Personalised recommendations