One of the important and computationally complex problems in graph theory is graph matching, i.e., finding a correspondence between the vertices of a pair of graphs. Modern rapidly developing methods are largely based on machine learning. We propose a new approach based on deep learning of a graph neuron network combining convolutional and Siamese techniques. This involves learning the metrics between graph vertices and then using these metrics for matching. Experiments on sets of real data demonstrate the usefulness of the proposed approach.
Similar content being viewed by others
References
F. Zhou and F. de la Torre, “Factorized graph matching,” 2012 IEEE Conference on Computer Vision and Pattern Recognition, IEEE (2012), pp. 127–134.
M. Neuhaus and H. Bunke, “A graph matching based approach to fingerprint classification using directional variantce,” Lectures Notes in Computer Science, Springer, 3546, 191–200 (2005).
S. Lajevardi, A. Arakala, S. Davis, and K. Horadam, “Verification system based on biometric graph matching,” IEEE Trans. Image Processing, 22, 3625–3635 (2013).
D. Bruschi, L. Martignoni, and M. Monga, “Detecting self-mutating malware using control-flow graph matching,” Lectures Notes in Computer Science, Springer, 4064, 129–143 (2006).
X. Yan, P. S. Yu, and J. Han, “Substructure similarity search in graph databses,” Proc. ACM SIGMOD Int. Conf. on Management of Data, ACM Press (2006), pp. 766–777.
W.-H. Tsai and K.-S. Fu, “Error-correcting isomorphisms of attributed relational graphs for pattern analysis,” IEEE Trans. on Systems, Man, and Cybernetics, 9, No. 12, 757–768 (1979).
J. Yan, X.-Ch. Yin, W. Lin, Ch. Deng, H. Zha, and X. Yan, “A short survey of recent advances in graph matching,” Proc. 2016 ACM Int. Conf. on Multimedia Retrieval, ACM (2016), pp. 167–174.
E. L. Lawler, “The quadratic assignment problem,” Management Science, 9, No. 4, 586–599 (1963).
M. Leordeanu and M. Hebert, “A spectral technique for correspondence problems using pairwise constraints,” Proc. IEEE Int. Conf. on Computer Vision, vol. II, IEEE (2005), pp. 1482–1489.
T. Cour, P. Srinivsan, and J. Shi, “Balanced graph matching,” Advances in Neutral Information Processing Systems, MIT Press (2006), pp. 313–320.
S. Gold and A. Rangarajan, “A graduated assignment algorithm for graph matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, 18, No. 4, 377–388 (1996).
M. Leordeanu, M. Hebert, and R. Sukthankar, “An integer projected fixed point method for graph matching and MAP inference,” Advances in Neutral Information Processing Systems, MIT Press, 1, No. 3, 1114–1122 (2009).
B. J. van Wyk and M. A. van Wyk, “A POCS-based graph matching algorithm,” IEEE Trans. Pattern Analysis and Machine Intelligence, 26, No. 11, 1526–1530 (2004).
T. S. Caetano, J. J. McAuley, L. Cheng, Q. V. Le, and A. J. Smola, “Learning graph matching,” IEEE Trans. Pattern Analysis and Machine Intelligence, 31, No. 6, 1048–1058 (2009).
M. Leordeanu, R. Sukthankar, and M. Hebert, “Unsupervised learning for graph matching,” Int. J. Computer Vision, 96, No. 1, 28–45 (2012).
A. Zanfir and C. Sminchisescu, “Deep learning of graph matching,” IEEE Conf. Computer Vision and Pattern Recognition, IEEE (2018), pp. 2684–2693.
T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolution networks,” 5th Int. Conf. on Learning Representation, ICLR 2017, Conference Track Proceedings (2019).
B. Kulis, “Metric learning: A survey,” Foundations and Trends in Machine Learning, 5, No. 4, 287–364 (2013).
C. Wah, S. Branson, P. Welinder, P. Perona, and S. Belongie, The Caltech UCSD Birds-200–2011 Dataset, California Institute of Technology (2011).
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. Ch.Chen, “MobileNetV2: Inverted residuals and linear bottleneckes,” Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, IEEE (2018), pp. 4510–4520.
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated from Prikladnaya Matematika i Informatika, No. 64, 2020, pp. 55–63.
Rights and permissions
About this article
Cite this article
Kozlov, V.D., Maisuradze, A.I. Metric Learning in Graph Matching Problems. Comput Math Model 31, 477–483 (2020). https://doi.org/10.1007/s10598-021-09509-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10598-021-09509-y