Abstract
Over-squashing and over-smoothing are two critical issues, that limit the capabilities of graph neural networks (GNNs). While over-smoothing eliminates the differences between nodes making them indistinguishable, over-squashing refers to the inability of GNNs to propagate information over long distances, as exponentially many node states are squashed into fixed-size representations. Both phenomena share similar causes, as both are largely induced by the graph topology. To mitigate these problems in graph classification tasks, we propose CurvPool, a novel pooling method. CurvPool exploits the notion of curvature of a graph to adaptively identify structures responsible for both over-smoothing and over-squashing. By clustering nodes based on the Balanced Forman curvature, CurvPool constructs a graph with a more suitable structure, allowing deeper models and the combination of distant information. We compare it to other state-of-the-art pooling approaches and establish its competitiveness in terms of classification accuracy, computational complexity, and flexibility. CurvPool outperforms several comparable methods across all considered tasks. The most consistent results are achieved by pooling densely connected clusters using the sum aggregation, as this allows additional information about the size of each pool.
C. Sanders and A. Roth—Equal contribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Alon, U., Yahav, E.: On the bottleneck of graph neural networks and its practical implications. arXiv preprint arXiv:2006.05205 (2020)
Bianchi, F.M., Grattarola, D., Alippi, C.: Spectral clustering with graph neural networks for graph pooling. In: International Conference on Machine Learning, pp. 874–883. PMLR (2020)
Bianchi, F.M., Lachi, V.: The expressive power of pooling in graph neural networks. arXiv preprint arXiv:2304.01575 (2023)
Blakely, D., Lanchantin, J., Qi, Y.: Time and space complexity of graph convolutional networks. Accessed 31 Dec 2021
Borgwardt, K.M., Ong, C.S., Schönauer, S., Vishwanathan, S.V.N., Smola, A.J., Kriegel, H.P.: Protein function prediction via graph kernels. Bioinformatics 21, i47–i56 (2005). https://doi.org/10.1093/bioinformatics/bti1007
Bron, C., Kerbosch, J.: Algorithm 457: finding all cliques of an undirected graph. Commun. ACM 16(9), 575–577 (1973)
Cai, C., Wang, Y.: A note on over-smoothing for graph neural networks. arXiv preprint arXiv:2006.13318 (2020)
Chen, D., Lin, Y., Li, W., Li, P., Zhou, J., Sun, X.: Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 3438–3445 (2020)
Diehl, F., Brunner, T., Le, M.T., Knoll, A.: Towards graph pooling by edge contraction. In: ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data (2019)
Du, J., Wang, S., Miao, H., Zhang, J.: Multi-channel pooling graph neural networks. In: IJCAI, pp. 1442–1448 (2021)
Eppstein, D., Löffler, M., Strash, D.: Listing all maximal cliques in large sparse real-world graphs. J. Exp. Algorithmics (JEA) 18, 3–1 (2013)
Fey, M., Yuen, J.G., Weichert, F.: Hierarchical inter-message passing for learning on molecular graphs. arXiv preprint arXiv:2006.12179 (2020)
Forman, R.: Bochner’s method for cell complexes and combinatorial Ricci curvature. Discrete Comput. Geom. 29, 323–374 (2003)
Gao, H., Chen, Y., Ji, S.: Learning graph pooling and hybrid convolutional operations for text representations. In: The World Wide Web Conference, pp. 2743–2749 (2019)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448–456. PMLR (2015)
Khasahmadi, A.H., Hassani, K., Moradi, P., Lee, L., Morris, Q.: Memory-based graph networks. arXiv preprint arXiv:2002.09518 (2020)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Lee, J., Lee, I., Kang, J.: Self-attention graph pooling. In: International Conference on Machine Learning, pp. 3734–3743. PMLR (2019)
Lei, F., Liu, X., Jiang, J., Liao, L., Cai, J., Zhao, H.: Graph convolutional networks with higher-order pooling for semisupervised node classification. Concur. Comput. Pract. Experience 34(16), e5695 (2022)
Li, J., Ma, Y., Wang, Y., Aggarwal, C., Wang, C.D., Tang, J.: Graph pooling with representativeness. In: 2020 IEEE International Conference on Data Mining (ICDM), pp. 302–311. IEEE (2020)
Li, Q., Han, Z., Wu, X.M.: Deeper insights into graph convolutional networks for semi-supervised learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Liu, N., Jian, S., Li, D., Zhang, Y., Lai, Z., Xu, H.: Hierarchical adaptive pooling by capturing high-order dependency for graph representation learning. IEEE Trans. Knowl. Data Eng. (2021)
Luzhnica, E., Day, B., Lio, P.: Clique pooling for graph classification. arXiv preprint arXiv:1904.00374 (2019)
Morris, C., et al.: Weisfeiler and Leman go neural: higher-order graph neural networks. Proc. AAAI Conf. Artif. Intell. 33, 4602–4609 (2019). https://doi.org/10.1609/aaai.v33i01.33014602
Nguyen, T., Grishman, R.: Graph convolutional networks with argument-aware pooling for event detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Noutahi, E., Beaini, D., Horwood, J., Giguère, S., Tossou, P.: Towards interpretable sparse graph representation learning with Laplacian pooling. arXiv preprint arXiv:1905.11577 (2019)
Nt, H., Maehara, T.: Revisiting graph neural networks: all we have is low-pass filters. arXiv preprint arXiv:1905.09550 (2019)
Ollivier, Y.: Ricci curvature of metric spaces. C.R. Math. 345(11), 643–646 (2007)
Ollivier, Y.: Ricci curvature of Markov chains on metric spaces. J. Funct. Anal. 256(3), 810–864 (2009)
Oono, K., Suzuki, T.: Graph neural networks exponentially lose expressive power for node classification. arXiv preprint arXiv:1905.10947 (2019)
Pan, S., Hu, R., Long, G., Jiang, J., Yao, L., Zhang, C.: Adversarially regularized graph autoencoder for graph embedding. arXiv preprint arXiv:1802.04407 (2018)
Ranjan, E., Sanyal, S., Talukdar, P.: ASAP: adaptive structure aware pooling for learning hierarchical graph representations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 5470–5477 (2020)
Roth, A., Liebig, T.: Forecasting unobserved node states with spatio-temporal graph neural networks. In: 2022 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 740–747. IEEE (2022)
Roth, A., Liebig, T.: Transforming PageRank into an infinite-depth graph neural network. In: Amini, M.R., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds.) Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 469–484. Springer, Cham (2022)
Tomita, E., Tanaka, A., Takahashi, H.: The worst-case time complexity for generating all maximal cliques and computational experiments. Theoret. Comput. Sci. 363(1), 28–42 (2006)
Topping, J., Di Giovanni, F., Chamberlain, B.P., Dong, X., Bronstein, M.M.: Understanding over-squashing and bottlenecks on graphs via curvature. arXiv preprint arXiv:2111.14522 (2021)
Wang, Y.G., Li, M., Ma, Z., Montufar, G., Zhuang, X., Fan, Y.: Haar graph pooling. In: International Conference on Machine Learning, pp. 9952–9962. PMLR (2020)
Watts, D.J.: Networks, dynamics, and the small-world phenomenon. Am. J. Sociol. 105(2), 493–527 (1999)
Wu, Z., et al.: MoleculeNet: a benchmark for molecular machine learning. Chem. Sci. 9(2), 513–530 (2018)
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018)
Yan, Y., Hashemi, M., Swersky, K., Yang, Y., Koutra, D.: Two sides of the same coin: heterophily and oversmoothing in graph convolutional neural networks. In: 2022 IEEE International Conference on Data Mining (ICDM), pp. 1287–1292. IEEE (2022)
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 (2015)
Ying, Z., You, J., Morris, C., Ren, X., Hamilton, W., Leskovec, J.: Hierarchical graph representation learning with differentiable pooling. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Yuan, H., Ji, S.: StructPool: structured graph pooling via conditional random fields. In: Proceedings of the 8th International Conference on Learning Representations (2020)
Zhang, M., Cui, Z., Neumann, M., Chen, Y.: An end-to-end deep learning architecture for graph classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Zhang, Y.D., Satapathy, S.C., Guttery, D.S., Górriz, J.M., Wang, S.H.: Improved breast cancer classification through combining graph convolutional network and convolutional neural network. Inf. Process. Manage. 58(2), 102439 (2021)
Zhao, H., Xie, J., Wang, H.: Graph convolutional network based on multi-head pooling for short text classification. IEEE Access 10, 11947–11956 (2022)
Acknowledgements
This research has been funded by the Federal Ministry of Education and Research of Germany and the state of North-Rhine Westphalia as part of the Lamarr-Institute for Machine Learning and Artificial Intelligence and by the Federal Ministry of Education and Research of Germany under grant no. 01IS22094E WEST-AI.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sanders, C., Roth, A., Liebig, T. (2025). Curvature-Based Pooling Within Graph Neural Networks. In: Meo, R., Silvestri, F. (eds) Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2023. Communications in Computer and Information Science, vol 2135. Springer, Cham. https://doi.org/10.1007/978-3-031-74633-8_35
Download citation
DOI: https://doi.org/10.1007/978-3-031-74633-8_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-74632-1
Online ISBN: 978-3-031-74633-8
eBook Packages: Artificial Intelligence (R0)