Explainability in subgraphs-enhanced Graph Neural Networks


  • Michele Guerra UiT the Arctic University of Norway
  • Indro Spinelli Sapienza University of Rome
  • Simone Scardapane Sapienza University of Rome
  • Filippo Maria Bianchi UiT the Arctic University of Norway & NORCE Norwegian Research Centre




explainability, GNN, graph, subgraphs


Recently, subgraphs-enhanced Graph Neural Networks (SGNNs) have been introduced to enhance the expressive power of Graph Neural Networks (GNNs), which was proved to be not higher than the 1-dimensional Weisfeiler-Leman isomorphism test.
The new paradigm suggests using subgraphs extracted from the input graph to improve the model's expressiveness, but the additional complexity exacerbates an already challenging problem in GNNs: explaining their predictions. In this work, we adapt PGExplainer, one of the most recent explainers for GNNs, to SGNNs. The proposed explainer accounts for the contribution of all the different subgraphs and can produce a meaningful explanation that humans can interpret. The experiments that we performed both on real and synthetic datasets show that our framework is successful in explaining the decision process of an SGNN on graph classification tasks.


B. Bevilacqua, F. Frasca, D. Lim, B. Srinivasan, C. Cai, G. Balamurugan, M. M. Bronstein, and H. Maron. Equivariant subgraph aggregation networks. arXiv preprint arXiv:2110.02910, 2021.

P. Dabkowski and Y. Gal. Real time image saliency for black box classifiers. Advances in neural information processing systems, 30, 2017.

G. Hinton, L. Deng, D. Yu, G. E. Dahl, A.-r. Mohamed, N. Jaitly, A. Senior, V. Vanhoucke, P. Nguyen, T. N. Sainath, et al. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal processing magazine, 29 (6):82–97, 2012.

J. Kazius, R. McGuire, and R. Bursi. Derivation and validation of toxicophores for mutagenicity prediction. Journal of medicinal chemistry, 48(1):312–320, 2005.

T. N. Kipf and M. Welling. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.

D. Luo, W. Cheng, D. Xu, W. Yu, B. Zong, H. Chen, and X. Zhang. Parameterized explainer for graph neural network. Advances in neural information processing systems, 33: 19620–19631, 2020.

C. J. Maddison, A. Mnih, and Y. W. Teh. The concrete distribution: A continuous relaxation of discrete random variables. In International Conference on Learning Representations, 2017.

C. Morris, M. Ritzert, M. Fey, W. L. Hamilton, J. E. Lenssen, G. Rattan, and M. Grohe. Weisfeiler and leman go neural: Higher-order graph neural networks. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 4602–4609, 2019.

B. Weisfeiler and A. Leman. The reduction of a graph to canonical form and the algebra which appears therein. NTI, Series, 2(9):12–16, 1968.

K. Xu, W. Hu, J. Leskovec, and S. Jegelka. How powerful are graph neural networks? In International Conference on Learning Representations, 2019.

Z. Ying, D. Bourgeois, J. You, M. Zitnik, and J. Leskovec. Gnnexplainer: Generating explanations for graph neural networks. Advances in neural information processing systems, 32, 2019.