Abstract
In recent years, deep learning researchers have been increasingly interested in developing architectures able to operate on data abstracted as graphs, i.e., Graph Neural Networks (GNNs). At the same time, there has been a surge in the number of commercial AI systems deployed for real-world applications. At their core, the majority of these systems are based on black-box deep learning models, such as GNNs, greatly limiting their accountability and trustworthiness. The idea underpinning this paper is to exploit the representational power of graph variational autoencoders to learn an embedding space where a “convolution” between local structures and latent vectors can take place. The key intuition is that this embedding space can then be used to decode the learned latent vectors into more interpretable latent structures. Our experiments validate the performance of our model against widely used alternatives on standard graph benchmarks, while also showing the ability to probe the model decisions by visualising the learned structural patterns.
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
Bai, L., Cui, L., Jiao, Y., Rossi, L., Hancock, E.: Learning backtrackless aligned-spatial graph convolutional networks for graph classification. IEEE Trans. Pattern Anal. Mach. Intell. (2020)
Bevilacqua, B., et al.: Equivariant subgraph aggregation networks. In: International Conference on Learning Representations (2022)
Bicciato, A., Cosmo, L., Minello, G., Rossi, L., Torsello, A.: Classifying me softly: a novel graph neural network based on features soft-alignment. In: S+SSPR, pp. 43–53. Springer (2022)
Bicciato, A., Cosmo, L., Minello, G., Rossi, L., Torsello, A.: GNN-LoFI: a novel graph neural network through localized feature-based histogram intersection. Pattern Recogn. 148, 110210 (2024)
Bouritsas, G., Frasca, F., Zafeiriou, S.P., Bronstein, M.: Improving graph neural network expressivity via subgraph isomorphism counting. IEEE Trans. Pattern Anal. Mach. Intell. (2022)
Cosmo, L., et al.: Graph kernel neural networks. IEEE Trans. Neural Netw. Learn. Syst. (2024)
Errica, F., Podda, M., Bacciu, D., Micheli, A.: A fair comparison of graph neural networks for graph classification. arXiv preprint arXiv:1912.09893 (2019)
Feng, A., You, C., Wang, S., Tassiulas, L.: Kergnns: interpretable graph neural networks with graph kernels. arXiv preprint arXiv:2201.00491 (2022)
Gallagher-Syed, A., et al.: Multi-stain self-attention graph multiple instance learning pipeline for histopathology whole slide images. arXiv preprint arXiv:2309.10650 (2023)
Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: International Conference on Machine Learning, pp. 1263–1272. PMLR (2017)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Lima, A., Rossi, L., Musolesi, M.: Coding together at scale: github as a collaborative social network. In: Proceedings of the International AAAI Conference on Web and Social Media, vol. 8, pp. 295–304 (2014)
Lockhart, J., Minello, G., Rossi, L., Severini, S., Torsello, A.: Edge centrality via the holevo quantity. In: Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshop, S+ SSPR 2016, Mérida, Mexico, 29 November–2 December 2016, Proceedings, pp. 143–152. Springer (2016)
Mehrish, A., Majumder, N., Bharadwaj, R., Mihalcea, R., Poria, S.: A review of deep learning techniques for speech processing. Inf. Fusion 99 (2023)
Morris, C., et al.: Weisfeiler and leman go neural: higher-order graph neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4602–4609 (2019)
Nikolentzos, G., Meladianos, P., Tixier, A.J.P., Skianis, K., Vazirgiannis, M.: Kernel graph convolutional neural networks. In: International Conference on Artificial Neural Networks, pp. 22–32. Springer (2018)
Roscher, R., Bohn, B., Duarte, M.F., Garcke, J.: Explainable machine learning for scientific insights and discoveries. IEEE Access 8, 42200–42216 (2020)
Said, A., Ahmad, O.U., Abbas, W., Shabbir, M., Koutsoukos, X.: Improving graph machine learning performance through feature augmentation based on network control theory. arXiv preprint arXiv:2405.03706 (2024)
Senior, H., Slabaugh, G., Yuan, S., Rossi, L.: Graph neural networks in vision-language image understanding: a survey. Vis. Comput. 1–26 (2024)
Simonovsky, M., Komodakis, N.: Dynamic edge-conditioned filters in convolutional neural networks on graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3693–3702 (2017)
Simonovsky, M., Komodakis, N.: Graphvae: towards generation of small graphs using variational autoencoders. In: Artificial Neural Networks and Machine Learning–ICANN 2018: 27th International Conference on Artificial Neural Networks, Rhodes, Greece, 4–7 October 2018, Proceedings, Part I 27, pp. 412–422. Springer (2018)
Sperduti, A., Starita, A.: Supervised neural networks for the classification of structures. IEEE Trans. Neural Netw. 8(3), 714–735 (1997)
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y., et al.: Graph attention networks. Stat 1050(20), 10–48550 (2017)
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? arXiv preprint arXiv:1810.00826 (2018)
Yi, H.C., You, Z.H., Huang, D.S., Kwoh, C.K.: Graph representation learning in bioinformatics: trends, methods and applications. Briefings Bioinform. 23(1), bbab340 (2022)
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., Yu, H., Gui, S., Ji, S.: Explainability in graph neural networks: a taxonomic survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(5), 5782–5799 (2022)
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)
Acknowledgments
This project is partially supported by the European Union with the program Next-GenerationEU. In particular, L.C. and A.B. are supported by PNRR - M.4 C.2, Investment 1.1 PRIN 2022 - project n. 2022AL45R2, EYE-FI.AI, CUP H53D2300350-0001. G.M. is supported by iNEST - Interconnected Nord-Est Innovation Ecosystem (iNEST ECS\(\_\)00000043 - CUP H43C22000540006). A.T.’s work was partially supported by the project “Perturbation problems and asymptotics for elliptic differential equations: variational and potential theoretic method” - PRIN 2022 - grant n. 2022SENJZ3.
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
Minello, G., Zhang, L., Bicciato, A., Rossi, L., Torsello, A., Cosmo, L. (2025). LESI-GNN: An Interpretable Graph Neural Network Based on Local Structures Embedding. In: Torsello, A., Rossi, L., Cosmo, L., Minello, G. (eds) Structural, Syntactic, and Statistical Pattern Recognition. S+SSPR 2024. Lecture Notes in Computer Science, vol 15444. Springer, Cham. https://doi.org/10.1007/978-3-031-80507-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-80507-3_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-80506-6
Online ISBN: 978-3-031-80507-3
eBook Packages: Computer ScienceComputer Science (R0)
