Abstract
Graph Neural Networks (GNNs) have garnered considerable attention due to their potential applications across multiple domains. However, enhancing their interpretability is a significant challenge for the crucial application. This paper proposes an innovative node perturbation-based method to explicate GNNs and unveil their decision-making processes. Categorized as a black-box method, it generates explanations of node importance solely through the input-output analysis of the model, obviating the necessity for internal access. The method employs fidelity as a metric for calculating the significance of perturbation masks and utilizes a sparsity threshold to filter the computation results. Furthermore, recognizing the impact of different node combinations on model prediction outcomes, we treat the mask as a random variable. By randomly sampling various masks, we compute perturbed node importance, facilitating the generation of user-friendly explanations. Comparative experiments and ablation studies conducted on both real and synthetic datasets substantiate the efficacy of our approach in interpreting GNNs. Additionally, through a case study, we visually demonstrate the method’s compelling interpretative evidence regarding model prediction outcomes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160 (2018)
Baldassarre, F., Azizpour, H.:. Explainability techniques for graph convolutional networks. arXiv preprint arXiv:1905.13686 (2019)
Dai, E., et al.: A comprehensive survey on trustworthy graph neural networks: privacy, robustness, fairness, and explainability. arXiv preprint arXiv:2204.08570 (2022)
Feng, Q., Liu, N., Yang, F., Tang, R., Du, M., Hu, X.: Degree: decomposition based explanation for graph neural networks. arXiv preprint arXiv:2305.12895 (2023)
Funke, T., Khosla, M., Rathee, M., Anand, A.: ZORRO: valid, sparse, and stable explanations in graph neural networks. IEEE Trans. Knowl. Data Eng. 35, 8687–8698 (2022)
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Comput. Surv. (CSUR) 51(5), 1–42 (2018)
Holdijk, L., Boon, M., Henckens, S., de Jong, L.: [re] parameterized explainer for graph neural network. In: ML Reproducibility Challenge 2020 (2021)
Huang, Q., Yamada, M., Tian, Y., Singh, D., Chang, Y.: GraphLIME: local interpretable model explanations for graph neural networks. IEEE Trans. Knowl. Data Eng. 35, 6968–6972 (2022)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Lucic, A., Ter Hoeve, M.A., Tolomei, G., De Rijke, M., Silvestri, F.: CF-GNNexplainer: counterfactual explanations for graph neural networks. In: International Conference on Artificial Intelligence and Statistics, pp. 4499–4511. PMLR (2022)
Luo, D., et al.: Parameterized explainer for graph neural network. In: Advance Neural Information Processing System, vol. 33, pp. 19620–19631 (2020)
Petsiuk, V., Das, A., Saenko, K.: Rise: randomized input sampling for explanation of black-box models. arXiv preprint arXiv:1806.07421 (2018)
Pope, P.E., Kolouri, S., Rostami, M., Martin, C.E., Hoffmann, H.: Explainability methods for graph convolutional neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10772–10781 (2019)
Schnake, T., et al.: Higher-order explanations of graph neural networks via relevant walks. IEEE Trans. Pattern Anal. Mach. Intell. 44(11), 7581–7596 (2021)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 618–626 (2017)
Shun, K.T.T., Limanta, E.E., Khan, A.: An evaluation of backpropagation interpretability for graph classification with deep learning. In: 2020 IEEE International Conference on Big Data (Big Data), pp. 561–570. IEEE (2020)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319–3328. PMLR (2017)
Vu, M., Thai, M.T.: PGM-Explainer: probabilistic graphical model explanations for graph neural networks. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12225–12235 (2020)
Wang, X., Wu, Y., Zhang, A., He, X., Chua, T.S.: Causal screening to interpret graph neural networks (2020)
Xuanyuan, H., Barbiero, P., Georgiev, D., Magister, L.C., Liò, P.: Global concept based interpretability for graph neural networks via neuron analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, pp. 10675–10683 (2023)
Ying, Z., Bourgeois, D., You, J., Zitnik, M., Leskovec, J.: GNNExplainer: generating explanations for graph neural networks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Yuan, H., Tang, J., Hu, X., Ji, S.: XGNN: towards model-level explanations of graph neural networks. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 430–438 (2020)
Yuan, H., Haiyang, Yu., Gui, S., Ji, S.: Explainability in graph neural networks: a taxonomic survey. IEEE Trans. Pattern Anal. Mach. Intell. 45(5), 5782–5799 (2022)
Zhang, S., Liu, Y., Shah, N., Sun, Y.: GStarX: explaining graph neural networks with structure-aware cooperative games. In: Advance Neural Information Processing System, vol. 35, pp. 19810–19823 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yang, X., Huang, H., Zuo, X. (2024). Random Mask Perturbation Based Explainable Method of Graph Neural Networks. In: Yang, DN., Xie, X., Tseng, V.S., Pei, J., Huang, JW., Lin, J.CW. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2024. Lecture Notes in Computer Science(), vol 14647. Springer, Singapore. https://doi.org/10.1007/978-981-97-2259-4_2
Download citation
DOI: https://doi.org/10.1007/978-981-97-2259-4_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2261-7
Online ISBN: 978-981-97-2259-4
eBook Packages: Computer ScienceComputer Science (R0)