Abstract
Recently, the Graph Convolutional Networks (GCNs) have achieved state-of-the-art performance in many graph data related tasks. However, traditional GCNs may generate redundant information in the message passing phase. In order to solve this problem, we propose a novel graph convolution named Push-and-Pull Convolution (PPC), which follows the message passing framework. On the one hand, for each star-shaped subgraph, PPC uses a node pair based message generation function to calculate the message pushed by each local node to the central node. On the other hand, in the message aggregation substep, each central node pulls valuable information from the messages pushed by its local nodes based on a gate network with pre-perceiving function. Based on the PPC, a new network named Push-and-Pull Graph Convolutional Network (PPGCN) is proposed for graph classification. PPGCN stacks multiple PPC layers to extend the receptive field of each node, then applies a global pooling layer to get the graph embedding based on the concatenation of all PPC layers’ outputs. The new network is permutation invariant and can be trained end-to-end. We evaluate the performance of PPGCN in 6 graph classification datasets. Compared with state-of-the-art baselines, PPGCN achieves the top-1 accuracy on 4 of 6 datasets.
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
References
Atwood, J., Towsley, D.: Diffusion-convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1993–2001 (2016)
Borgwardt, K.M., Kriegel, H.P.: Shortest-path kernels on graphs. In: Fifth IEEE International Conference on Data Mining (ICDM 2005), pp. 8. IEEE (2005)
Fey, M., Lenssen, J.E.: Fast graph representation learning with pytorch geometric. arXiv preprint arXiv:1903.02428 (2019)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: Proceedings of the 34th International Conference on Machine Learning, pp. 1263–1272 (2017)
Ivanov, S., Burnaev, E.: Anonymous walk embeddings. In: Proceedings of the 35th International Conference on Machine Learning, pp. 2191–2200 (2018)
Karp, R., Schindelhauer, C., Shenker, S., Vocking, B.: Randomized rumor spreading. In: Proceedings 41st Annual Symposium on Foundations of Computer Science, pp. 565–574 (2000)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Mallea, M.D.G., Meltzer, P., Bentley, P.J.: Capsule neural networks for graph classification using explicit tensorial graph representations. arXiv preprint arXiv:1902.08399 (2019)
Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: International Conference on Machine Learning, pp. 2014–2023 (2016)
Shervashidze, N., Schweitzer, P., Leeuwen, E.J.V., Mehlhorn, K., Borgwardt, K.M.: Weisfeiler-Lehman graph kernels. J. Mach. Learn. Res. 12, 2539–2561 (2011)
Shervashidze, N., Vishwanathan, S., Petri, T., Mehlhorn, K., Borgwardt, K.: Efficient graphlet kernels for large graph comparison. In: Artificial Intelligence and Statistics, pp. 488–495 (2009)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
Verma, S., Zhang, Z.L.: Graph capsule convolutional neural networks. arXiv preprint arXiv:1805.08090 (2018)
Vishwanathan, S.V.N., Schraudolph, N.N., Kondor, R., Borgwardt, K.M.: Graph kernels. J. Mach. Learn. Res. 11, 1201–1242 (2010)
Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. arXiv preprint arXiv:1801.07829 (2018)
Weisfeiler, B., Lehman, A.A.: A reduction of a graph to a canonical form and an algebra arising during this reduction. Nauchno-Technicheskaya Informatsia 2(9), 12–16 (1968)
Xu, K., Li, C., Tian, Y., Sonobe, T., Kawarabayashi, K.I., Jegelka, S.: Representation learning on graphs with jumping knowledge networks. arXiv preprint arXiv:1806.03536 (2018)
Yanardag, P., Vishwanathan, S.V.N.: Deep graph kernels. In: Proceedings of the 21th ACM SIGKDD 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 Thirty-Second AAAI Conference on Artificial Intelligence, pp. 4438–4445 (2018)
Acknowledgement
This research is partially supported by the National Natural Science Foundation of China (Grant No. 61562041, Grant No. 61866018); Jiangsu Provincial Natural Science Foundation of China (Grant No. BK20171447); Jiangsu Provincial University Natural Science Research of China (Grant No. 17KJB520024).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, X., Liu, Z., Qu, Y. (2019). PPGCN: A Message Selection Based Approach for Graph Classification. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1142. Springer, Cham. https://doi.org/10.1007/978-3-030-36808-1_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-36808-1_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36807-4
Online ISBN: 978-3-030-36808-1
eBook Packages: Computer ScienceComputer Science (R0)