Abstract
Graph Neural Networks (GNNs) have achieved remarkable success in many aspects, but they still suffer from certain limitations, such as over-smoothing with increasing layer depth, sensitivity to topological perturbations, and inability to be applied to heterophilic graphs. So this paper proposes a Multi-scale Information Fusion Adaptive Propagation Network (MAPNET) to overcome these limitations. First, a new graph data augmentation method is designed, which deletes unimportant edges and introduces KNN graphs to perturb the graph structure, and adds the graph regularization terms to improve the model’s robustness and generalization; second, a multi-scale information fusion adaptive propagation process is designed to enhance the diversity of neighborhoods to alleviate the over-smoothing problem; finally, the edge weights are extended to the negative values to adapt to the heterophilic graphs. Experimental results show that MAPNET partially solves the over-smoothing problem in GNNs. The model outperforms recent models in both semi-supervised and fully supervised node classification tasks on multiple datasets, and has better generalization performance and robustness.
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
Wu, Z., Pan, S., Chen, F., et al.: A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 32(1), 4–24 (2021). https://doi.org/10.1109/TNNLS.2020.2978386
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016). https://github.com/tkipf/pygcn
You, J., Ying, R., Leskovec, J.: Position-aware graph neural networks. In: International Conference on Machine Learning, pp. 7134–7143. PMLR (2019)
Fan, W., Ma, Y., Li, Q., et al.: Graph neural networks for social recommendation. In: The World Wide Web Conference, pp. 417–426 (2019). https://doi.org/10.1145/3308558.3313488
Berg, R., Kipf, T.N., Welling, M.: Graph convolutional matrix completion. arXiv preprint arXiv:1706.02263 (2017)
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in Neural Information Processing Systems, vol. 29 (2016)
Veličković, P., Cucurull, G., Casanova, A., et al.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Klicpera, J., Bojchevski, A., Günnemann, S.: Predict then propagate: graph neural networks meet personalized pagerank. arXiv preprint arXiv:1810.05997 (2018)
Xu, K., Li, C., Tian, Y., et al.: Representation learning on graphs with jumping knowledge networks. In: International Conference on Machine Learning, pp. 5453–5462. PMLR (2018)
Klicpera, J., Weißenberger, S., Günnemann, S.: Diffusion improves graph learning. arXiv preprint arXiv:1911.05485 (2019)
Liu, M., Gao, H., Ji, S.: Towards deeper graph neural networks. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 338–348 (2020). https://doi.org/10.1145/3394486.3403076
Rong, Y., Huang, W., Xu, T., et al.: DropEdge: towards deep graph convolutional networks on node classification. arXiv preprint arXiv:1907.10903 (2019)
Feng, W., Zhang, J., Dong, Y., et al.: Graph random neural networks for semi-supervised learning on graphs. In: Advances in Neural Information Processing Systems, vol. 33 (2020)
Wang, Y., Wang, W., Liang, Y., et al.: NodeAug: semi-supervised node classification with data augmentation. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 207–217 (2020). https://doi.org/10.1145/3394486.3403063
Chien, E., Peng, J., Li, P., et al.: Adaptive universal generalized pagerank graph neural network. arXiv preprint arXiv:2006.07988 (2020)
Pei, H., Wei, B., Chang, K.C.C., et al.: Geom-GCN: geometric graph convolutional networks. arXiv preprint arXiv:2002.05287 (2020). https://github.com/graphdml-uiuc-jlu/geom-gcn
Bo, D., Wang, X., Shi, C., et al.: Beyond low-frequency information in graph convolutional networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 5, pp. 3950–3957 (2021). https://doi.org/10.1609/aaai.v35i5.16514
Yang, L., Li, M., Liu, L., et al.: Diverse message passing for attribute with heterophily. In: Advances in Neural Information Processing Systems, vol. 34, pp. 4751–4763 (2021)
He, M., Wei, Z., Xu, H.: BernNet: learning arbitrary graph spectral filters via Bernstein approximation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 14239–14251 (2021)
Bo, D., Hu, B.B., Wang, X., et al.: Regularizing graph neural networks via consistency-diversity graph augmentations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 4, pp. 3913–3921 (2022). https://doi.org/10.1609/aaai.v36i4.20307
Yang, H., Ma, K., Cheng, J.: Rethinking graph regularization for graph neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 5, pp. 4573–4581 (2021). https://doi.org/10.1609/aaai.v35i5.16586
Ma, Q., Fan, Z., Wang, C., et al.: Graph mixed random network based on PageRank. Symmetry 14(8), 1678 (2022). https://doi.org/10.3390/sym14081678
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, Q., Wang, C., Fan, Z., Qian, Y. (2023). Adaptive Propagation Network Based on Multi-scale Information Fusion. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14261. Springer, Cham. https://doi.org/10.1007/978-3-031-44198-1_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-44198-1_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44197-4
Online ISBN: 978-3-031-44198-1
eBook Packages: Computer ScienceComputer Science (R0)