Abstract
The graph neural network can use the network topology, the attributes and labels of nodes to mine the potential relationships on network. In paper, we propose a graph convolutional network based on higher-order Neighborhood Aggregation. First, an improved graph convolutional module is proposed, which can more flexibly aggregate higher-order neighborhood information in convolution kernel. It alleviates the over-smooth problem caused by high-order aggregation to a certain extent. Then, we propose two different neighborhood aggregation models. The first model trains multiple embeddings independently for the network and obtains the final embedding through connection, that is, focuses on processing the overall information of the neighborhood. The other is analogous to the three-dimensional convolutional neural network on image. It concatenates features in each layer which pays more attention to processing the hierarchical information of the neighborhood. Our algorithm is a general network model enhancement algorithm which is suitable for different network architectures. Experiments on 6 real network datasets show that our algorithm has good results in node classification, link prediction, etc.
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
Cao, S., Lu, W., Xu, Q.: Grarep: learning graph representations with global structural information. In: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pp. 891–900 (2015)
Chen, J., Ma, T., Xiao, C.: Fastgcn: fast learning with graph convolutional networks via importance sampling. In: Proceedings of the 6th International Conference on Learning Representations (2018)
Hammond, D.K., Vandergheynst, P., Gribonval, R.: Wavelets on graphs via spectral graph theory. Appl. Comput. Harmonic Anal. 30(2), 129–150 (2011)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th International Conference on Learning Representations (2017)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. arXiv preprint arXiv:1611.07308 (2016)
Li, Q., Wu X, M., Liu, H., et al.: Label efficient semi-supervised learning via graph filtering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9582–9591 (2019)
McAuley, J.J., Leskovec, J.: Learning to discover social circles in ego networks. In: Conference and Workshop on Neural Information Processing Systems, pp. 548–556 (2012)
Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701–710 (2014)
Rossi, R., Ahmed, N.: The network data repository with interactive graph analytics and visualization. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 29, no. 1 (2015)
Sen, P., Namata, G., Bilgic, M., et al.: Collective classification in network data. AI Mag. 29(3), 93–93 (2008)
Tang, J., Qu, M., Wang, M., et al.: Line: large-scale information network embedding. In: Proceedings of the 24th International Conference on World Wide Web, pp. 1067–1077 (2015)
Veličković, P., Cucurull, G., Casanova, A., et al.: Graph attention networks. In: Proceedings of the 6th International Conference on Learning Representations (2018)
Velickovic, P., Fedus, W., Hamilton W, L., et al.: Deep graph infomax. In: Proceedings of the 7th International Conference on Learning Representations (2019)
Watts D.J., Strogatz S.H.: Collective dynamics of ’small-world’ networks. Nature 393(6684), 440–442 (1998)
Wu, F., Souza, A., Zhang, T., et al.: Simplifying graph convolutional networks. In: International conference on machine learning, PMLR, pp. 6861–6871 (2019)
Xu, B., Shen, H., Cao, Q., et al.: Graph convolutional networks using heat kernel for semi- supervised learning. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp. 1928–1934 (2019)
Acknowledgments
This work was supported by the National Natural Science Foundation of China under Grant 61773348.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, GF., Yang, XH., Ye, L., Huang, YJ., Jiang, P. (2021). Graph Convolutional Network Based on Higher-Order Neighborhood Aggregation. In: Mantoro, T., Lee, M., Ayu, M.A., Wong, K.W., Hidayanto, A.N. (eds) Neural Information Processing. ICONIP 2021. Communications in Computer and Information Science, vol 1516. Springer, Cham. https://doi.org/10.1007/978-3-030-92307-5_39
Download citation
DOI: https://doi.org/10.1007/978-3-030-92307-5_39
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92306-8
Online ISBN: 978-3-030-92307-5
eBook Packages: Computer ScienceComputer Science (R0)