Weighted Graph Classification by Self-Aligned Graph Convolutional Networks Using Self-Generated Structural Features
Directed weighted graphs are important graph data. The weights and directions of the edges carry rich information which can be utilized in many areas. For instance, in a cashflow network, the direction and amount of a transfer can be used to detect social ties or criminal organizations. Hence it is important to study the weighted graph classification problems. In this paper, we present a graph classification algorithm called Self-Aligned graph convolutional network (SA-GCN) for weighted graph classification. SA-GCN first normalizes a given graph so that graphs are trimmed and aligned in correspondence. Following that structural features are extracted from the edge weights and graph structures. And finally the model is trained in an adversarial way to make the model more robust. Experiments on benchmark datasets showed that the proposed model could achieve competitive results and outperformed some popular state-of-the-art graph classification methods.
KeywordsGraph classification Graph convolutional networks Graph normalization Structural features Adversarial training
This work is partially supported by the NSFC under grants Nos. 61673018, 61272338, 61703443 and Guangzhou Science and Technology Founding Committee under grant No. 201804010255 and Guangdong Province Key Laboratory of Computer Science.
- 1.Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: OSDI 2016, pp. 265–283 (2016)Google Scholar
- 3.Bruna, J., Zaremba, W., Szlam, A., Lecun, Y.: Spectral networks and locally connected networks on graphs. In: International Conference on Learning Representations (2014)Google Scholar
- 4.Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems, pp. 3844–3852 (2016)Google Scholar
- 6.Goodfellow, I., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples (2015)Google Scholar
- 11.Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: Proceedings of the 33rd International Conference on Machine Learning, pp. 2014–2023 (2016)Google Scholar
- 12.Page, L., Brin, S., Motwani, R., Winograd, T.: The PageRank citation ranking: bringing order to the web. Technical report, Stanford InfoLab (1999)Google Scholar
- 13.Shervashidze, N., Borgwardt, K.M.: Fast subtree kernels on graphs. In: Advances in Neural Information Processing Systems, pp. 1660–1668 (2009)Google Scholar
- 18.Weisfeiler, B., Lehman, A.A.: A reduction of a graph to a canonical form and an algebra arising during this reduction. Nauchno-Tech. Informatsiya 2(9), 12–16 (1968)Google Scholar
- 19.Yanardag, P., Vishwanathan, S.: Deep graph kernels. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1365–1374. ACM (2015)Google Scholar
- 20.Zhang, M., Cui, Z., Neumann, M., Chen, Y.: An end-to-end deep learning architecture for graph classification (2018)Google Scholar