Abstract
The problem of finding a distance and a correspondence between a pair of graphs is commonly referred to as the Error-tolerant Graph matching problem. The Graph Edit Distance is one of the most popular approaches to solve this problem. This method needs to define a set of parameters and the cost functions aprioristically. On the other hand, in recent years, Deep Neural Networks have shown very good performance in a wide variety of domains due to their robustness and ability to solve non-linear problems. The aim of this paper is to present a model to compute the assignments costs for the Graph Edit Distance by means of a Deep Neural Network previously trained with a set of pairs of graphs properly matched. We empirically show a major improvement using our method with respect to the state-of-the-art results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Conte, D., Foggia, P., Sansone, C., Vento, M.: Thirty years of graph matching in pattern recognition. Int. J. Pattern Recogn. Artif. Intell. 18(3), 265–298 (2004)
Bunke, H., Allermann, G.: Inexact graph matching for structural pattern recognition. Pattern Recogn. Lett. 1(4), 245–253 (1983)
Serratosa, F., Cortés, X.: Graph edit distance: moving from global to local structure to solve the graph-matching problem. Pattern Recogn. Lett. 65, 204–210 (2015)
Caetano, T.S., McAuley, J.J., Cheng, L., Le, Q.V., Smola, A.J.: Learning graph matching. IEEE Trans. Pattern Anal. Mach. Intell. 31(6), 1048–1058 (2009)
Cortés, X., Serratosa, F.: Learning graph matching substitution weights based on the ground truth node correspondence. IJPRAI 30(2) (2016)
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Raveaux, R., Martineau, M., Conte, D., Venturini, G.: Learning graph matching with a graph-based perceptron in a classification context. In: Foggia, P., Liu, C.-L., Vento, M. (eds.) GbRPR 2017. LNCS, vol. 10310, pp. 49–58. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-58961-9_5
Neuhaus, M., Bunke, H.: Self-organizing maps for learning the edit costs in graph matching. IEEE Trans. Syst. Man Cybern. Part B 35(3), 503–514 (2005)
Neuhaus, M., Bunke, H.: Automatic learning of cost functions for graph edit distance. Inf. Sci. 177(1), 239–247 (2007)
Leordeanu, M., Sukthankar, R., Hebert, M.: Unsupervised learning for graph matching. Int. J. Comput. Vis. 96(1), 28–45 (2012)
Serratosa, F., Solé-Ribalta, A., Cortés, X.: Automatic learning of edit costs based on interactive and adaptive graph recognition. In: Jiang, X., Ferrer, M., Torsello, A. (eds.) GbRPR 2011. LNCS, vol. 6658, pp. 152–163. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-20844-7_16
Cortés, X., Serratosa, F.: Learning graph-matching edit-costs based on the optimality of the oracle’s node correspondences. Pattern Recogn. Lett. 56, 22–29 (2015)
Riesen, K., Ferrer, M.: Predicting the correctness of node assignments in bipartite graph matching. Pattern Recogn. Lett. 69, 8–14 (2016)
Kanzow, C., Yamashita, N., Fukushima, M.: Levenberg-Marquardt methods with strong local convergence properties for solving nonlinear equations with convex constraints. JCAM 172(2), 375–397 (2004)
Riesen, K., Bunke, H.: Approximate graph edit distance computation by means of bipartite graph matching. Image Vis. Comput. 27(4), 950–959 (2009)
Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Log. Q. 2, 83–97 (1955)
Moreno-García, C.F., Cortés, X., Serratosa, F.: A graph repository for learning error-tolerant graph matching. In: Robles-Kelly, A., Loog, M., Biggio, B., Escolano, F., Wilson, R. (eds.) S+SSPR 2016. LNCS, vol. 10029, pp. 519–529. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49055-7_46
Acknowledgments
This work is part of the LUMINEUX project supported by the Region Centre-Val de Loire (France) and by the Spanish projects TIN2016-77836-C2-1-R and ColRobTransp MINECO DPI2016-78957-R AEI/FEDER EU; and also, the European project AEROARMS, H2020-ICT-2014-1-644271.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Cortés, X., Conte, D., Cardot, H., Serratosa, F. (2018). A Deep Neural Network Architecture to Estimate Node Assignment Costs for the Graph Edit Distance. In: Bai, X., Hancock, E., Ho, T., Wilson, R., Biggio, B., Robles-Kelly, A. (eds) Structural, Syntactic, and Statistical Pattern Recognition. S+SSPR 2018. Lecture Notes in Computer Science(), vol 11004. Springer, Cham. https://doi.org/10.1007/978-3-319-97785-0_31
Download citation
DOI: https://doi.org/10.1007/978-3-319-97785-0_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97784-3
Online ISBN: 978-3-319-97785-0
eBook Packages: Computer ScienceComputer Science (R0)