Abstract
Graph Neural Networks (GNNs) have shown powerful performance on various graph-related tasks. GNNs learn better knowledge representations by aggregating the features of neighboring nodes. However, the black-box representations of deep learning models make it difficult for people to understand GNN’s inherent operation mechanism. To this end, in this paper, we propose a model-agnostic method called GNN Prediction Interpreter (GPI) to explain node features’ effect on the prediction of GNN. Particularly, GPI first quantifies the correlation between node features and GNN’s prediction, and then identifies the subset of node features that have an essential impact on GNN’s prediction according to the quantitative results. Experiments demonstrate that GPI can provide better explanations than state-of-the-art methods.
Z. Zhang—Supported by the China Postdoctoral Science Foundation under Grant No. 2021M703273.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baldassarre, F., Azizpour, H.: Explainability techniques for graph convolutional networks. arXiv preprint arXiv:1905.13686 (2019)
Cover, T.M.: Elements of Information Theory. Wiley, Hoboken (1999)
Guan, C., Wang, X., Zhang, Q., Chen, R., He, D., Xie, X.: Towards a deep and unified understanding of deep neural models in NLP. In: ICLR (2019)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS (2017)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2016)
Li, G., Muller, M., Thabet, A., Ghanem, B.: DeepGCNs: can GCNs go as deep as CNNs? In: Proceedings of the IEEE International Conference on Computer Vision, pp. 9267–9276 (2019)
Lundberg, S., Lee, S.I.: A unified approach to interpreting model predictions. In: NIPS (2017)
Morris, C., et al.: Weisfeiler and leman go neural: Higher-order graph neural networks. In: AAAI (2019)
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)
Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: International Conference on Machine Learning, pp. 3145–3153. PMLR (2017)
Tu, C., Liu, H., Liu, Z., Sun, M.: Cane: context-aware network embedding for relation modeling. In: ACL (2017)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)
Verma, S., Zhang, Z.L.: Stability and generalization of graph convolutional neural networks. In: KDD (2019)
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: Derivation and validation of toxicophores for mutagenicity prediction. J. Med. Chem. (2005)
Ying, Z., Bourgeois, D., You, J., Zitnik, M., Leskovec, J.: GNNExplainer: generating explanations for graph neural networks. In: NIPS (2019)
Ying, Z., You, J., Morris, C., Ren, X., Hamilton, W., Leskovec, J.: Hierarchical graph representation learning with differentiable pooling. In: NIPS (2018)
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 and Data Mining, pp. 430–438 (2020)
Yuan, H., Yu, H., Gui, S., Ji, S.: Explainability in graph neural networks: a taxonomic survey. arXiv preprint arXiv:2012.15445 (2020)
Zhang, M., Chen, Y.: Link prediction based on graph neural networks. In: NIPS (2018)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Q., Zhang, Z., Diao, B., Xu, Y., Li, C. (2022). Towards Understanding the Effect of Node Features on the Predictions of Graph Neural Networks. In: Pimenidis, E., Angelov, P., Jayne, C., Papaleonidas, A., Aydin, M. (eds) Artificial Neural Networks and Machine Learning – ICANN 2022. ICANN 2022. Lecture Notes in Computer Science, vol 13530. Springer, Cham. https://doi.org/10.1007/978-3-031-15931-2_58
Download citation
DOI: https://doi.org/10.1007/978-3-031-15931-2_58
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-15930-5
Online ISBN: 978-3-031-15931-2
eBook Packages: Computer ScienceComputer Science (R0)