Abstract
Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling. In particular, image pooling transforms a connected discrete lattice into a reduced lattice with the same connectivity and allows reduction functions to consider all pixels in an image. However, there is no pooling that satisfies these properties for graphs. In fact, traditional graph pooling methods suffer from at least one of the following drawbacks: Graph disconnection or overconnection, low decimation ratio, and deletion of large parts of graphs. In this paper, we present three pooling methods based on the notion of maximal independent sets that avoid these pitfalls. Our experimental results confirm the relevance of maximal independent set constraints for graph pooling.
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
Anis, A., Gadde, A., Ortega, A.: Towards a sampling theorem for signals on arbitrary graphs. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3864–3868. IEEE (2014)
Balcilar, M., Guillaume, R., Héroux, P., Gaüzère, B., Adam, S., Honeine, P.: Analyzing the expressive power of graph neural networks in a spectral perspective. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)
Bianchi, F.M., Grattarola, D., Livi, L., Alippi, C.: Hierarchical representation learning in graph neural networks with node decimation pooling. IEEE Trans. Neural Netw. Learn. Syst. 33(5), 2195–2207 (2022)
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)
Dobson, P.D., Doig, A.J.: Distinguishing enzyme structures from non-enzymes without alignments. J. Molecul. Biol. 330(4), 771–783 (2003)
Errica, F., Podda, M., Bacciu, D., Micheli, A.: A fair comparison of graph neural networks for graph classification. arXiv preprint arXiv:1912.09893 (2019)
Gao, H., Ji, S.: Graph u-nets. In: International Conference on Machine Learning, pp. 2083–2092. PMLR (2019)
Hamilton, W.L.: Graph representation learning. Synth. Lect. Artif. Intell. Mach. Learn. 14(3), 1–159 (2020)
Haxhimusa, Y.: The Structurally Optimal Dual Graph Pyramid and Its Application in Image Partitioning, vol. 308. IOS Press (2007)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR) (2017)
Landolfi, F.: Revisiting edge pooling in graph neural networks. In: ESANN (2022)
Lee, J., Lee, I., Kang, J.: Self-attention graph pooling. In: International Conference on Machine Learning, pp. 3734–3743. PMLR (2019)
Meer, P.: Stochastic image pyramids. Comput. Vis. Graph. Image Process. 45(3), 269–294 (1989)
Stanovic, S., Gaüzère, B., Brun, L.: Maximal independent vertex set applied to graph pooling. In: Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshops, S+ SSPR 2022, Montreal, 26–27 August 2022, Proceedings, pp. 11–21. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-23028-8_2
Tanaka, Y., Eldar, Y.C., Ortega, A., Cheung, G.: Sampling signals on graphs: from theory to applications. IEEE Signal Process. Magaz. 37(6), 14–30 (2020)
Verma, N., Boyer, E., Verbeek, J.: Feastnet: feature-steered graph convolutions for 3d shape analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2598–2606 (2018)
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. Adv. Neural Inf. Process. Syst. 31, 4805–4815 (2018)
Zhang, M., Cui, Z., Neumann, M., Chen, Y.: An end-to-end deep learning architecture for graph classification. Proc. AAAI Conf. Artif. Intell. 32(1), 4438–4445 (2018)
Acknowledgments
The work reported in this paper was supported by French ANR grant #ANR-21-CE23-0025 CoDeGNN and was performed using HPC resources from GENCI-IDRIS (Grant 2022-AD011013595) and computing resources of CRIANN (Grant 2022001, Normandy, France).
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
Stanovic, S., Gaüzère, B., Brun, L. (2023). Maximal Independent Sets for Pooling in Graph Neural Networks. In: Vento, M., Foggia, P., Conte, D., Carletti, V. (eds) Graph-Based Representations in Pattern Recognition. GbRPR 2023. Lecture Notes in Computer Science, vol 14121. Springer, Cham. https://doi.org/10.1007/978-3-031-42795-4_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-42795-4_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42794-7
Online ISBN: 978-3-031-42795-4
eBook Packages: Computer ScienceComputer Science (R0)
