Abstract
Graph kernels have proven to be a promising approach for tackling the graph similarity and learning tasks at the same time. Most graph kernels are instances of the R-convolution framework. These kernels decompose graphs into their substructures and sum over all pairs of these substructures. A more promising family of kernels are the assignment kernels, which compute a matching between substructures of two objects such that the total similarity between the matched substructures is maximum. In this paper, we present a kernel which compares graphs by computing an assignment of their node embeddings. After embedding the vertices of all graphs in a vector space, we construct a hierarchy of the vertices using a clustering algorithm. Based on this hierarchy, we define a kernel that computes an optimal assignment of the vertices of two graphs. The proposed kernel is evaluated on several graph classification datasets. Our results indicate that the proposed approach is competitive with traditional and state-of-the-art techniques.
C. Wu is supported by the project “ESIGMA” (ANR-17-CE40-0028).
G. Nikolentzos is supported by the project “ESIGMA” (ANR-17-CE40-0028).
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
Notes
- 1.
The datasets are available at https://ls11-www.cs.tu-dortmund.de/staff/morris/graphkerneldatasets.
- 2.
Code available at https://github.com/ChangminWu/assignment-kernel-embeddings.
References
Barla, A., Odone, F., Verri, A.: Histogram intersection kernel for image classification. In: Proceedings of the 2003 International Conference on Image Processing, vol. 3, pp. III–513–16 (2003)
Borgwardt, K.M., Kriegel, H.: Shortest-path kernels on graphs. In: Proceedings of the 5th International Conference on Data Mining, pp. 74–81 (2005)
Chang, C., Lin, C.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 27 (2011)
Dhillon, I.S., Modha, D.S.: Concept decompositions for large sparse text data using clustering. Mach. Learn. 42(1), 143–175 (2001)
Donnat, C., Zitnik, M., Hallac, D., Leskovec, J.: Learning structural node embeddings via diffusion wavelets. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1320–1329. ACM (2018)
Fröhlich, H., Wegner, J.K., Sieker, F., Zell, A.: Optimal assignment kernels for attributed molecular graphs. In: Proceedings of the 22nd International Conference on Machine Learning, pp. 225–232 (2005)
Gascon, H., Yamaguchi, F., Arp, D., Rieck, K.: Structural detection of android malware using embedded call graphs. In: Proceedings of the 2013 Workshop on Artificial intelligence and Security, pp. 45–54 (2013)
Haussler, D.: Convolution kernels on discrete structures. Technical report, Department of Computer Science, University of California at Santa Cruz (1999)
Kondor, R., Son, H.T., Pan, H., Anderson, B., Trivedi, S.: Covariant Compositional Networks For Learning Graphs. arXiv preprint arXiv:1801.02144 (2018)
Kriege, N.M., Giscard, P.L., Wilson, R.: On valid optimal assignment kernels and applications to graph classification. In: Advances in Neural Information Processing Systems, pp. 1623–1631 (2016)
Lee, J.B., Rossi, R., Kong, X.: Graph classification using structural attention. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1666–1674. ACM (2018)
Morris, C., Ritzert, M., Fey, M., Hamilton, W.L., Lenssen, J.E., Rattan, G., Grohe, M.: Weisfeiler and leman go neural: higher-order graph neural networks. arXiv preprint arXiv:1810.02244 (2018)
Nikolentzos, G., Meladianos, P., Vazirgiannis, M.: Matching node embeddings for graph similarity. In: Proceedings of the 31st AAAI Conference in Artificial Intelligence, pp. 1891–1901 (2017)
Nikolentzos, G., Meladianos, P., Rousseau, F., Stavrakas, Y., Vazirgiannis, M.: Shortest-path graph kernels for document similarity. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1890–1900 (2017)
Nikolentzos, G., Siglidis, G., Vazirgiannis, M.: Graph Kernels: A Survey. arXiv preprint arXiv:1904.12218 (2019)
Ramon, J., Gärtner, T.: Expressivity versus efficiency of graph kernels. In: Proceedings of the 1st International Workshop on Mining Graphs, Trees and Sequences, pp. 65–74 (2003)
Ribeiro, L.F., Saverese, P.H., Figueiredo, D.R.: Struc2vec: learning node representations from structural identity. In: Proceedings of the 23rd International Conference on Knowledge Discovery and Data Mining, pp. 385–394 (2017)
Schölkopf, B., Tsuda, K., Vert, J.P.: Kernel Methods in Computational Biology. MIT Press, Cambridge (2004)
Shervashidze, N., Petri, T., Mehlhorn, K., Borgwardt, K.M., Vishwanathan, S.: Efficient graphlet kernels for large graph comparison. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, pp. 488–495 (2009)
Shervashidze, N., Schweitzer, P., Van Leeuwen, E.J., Mehlhorn, K., Borgwardt, K.M.: Weisfeiler-lehman graph kernels. J. Mach. Learn. Res. 12, 2539–2561 (2011)
Swain, M.J., Ballard, D.H.: Color indexing. Int. J. Comput. Vis. 7(1), 11–32 (1991)
Vert, J.P.: The optimal assignment kernel is not positive definite. arXiv preprint arXiv:0801.4061 (2008)
Yanardag, P., Vishwanathan, S.: Deep graph kernels. In: Proceedings of the 21th International Conference on Knowledge Discovery and Data Mining, pp. 1365–1374 (2015)
Zhang, M., Cui, Z., Neumann, M., Chen, Y.: An end-to-end deep learning architecture for graph classification. In: Proceedings of the 32nd AAAI Conference in Artificial Intelligence (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wu, C., Nikolentzos, G., Vazirgiannis, M. (2020). Matching Node Embeddings Using Valid Assignment Kernels. In: Cherifi, H., Gaito, S., Mendes, J., Moro, E., Rocha, L. (eds) Complex Networks and Their Applications VIII. COMPLEX NETWORKS 2019. Studies in Computational Intelligence, vol 881. Springer, Cham. https://doi.org/10.1007/978-3-030-36687-2_67
Download citation
DOI: https://doi.org/10.1007/978-3-030-36687-2_67
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36686-5
Online ISBN: 978-3-030-36687-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)