Demystifying Graph Neural Network Explanations

Graph neural networks (GNNs) are quickly becoming the standard approach for learning on graph structured data across several domains, but they lack transparency in their decision-making. Several perturbation-based approaches have been developed to provide insights into the decision making process of GNNs. As this is an early research area, the methods and data used to evaluate the generated explanations lack maturity. We explore these existing approaches and identify common pitfalls in three main areas: (1) synthetic data generation process, (2) evaluation metrics, and (3) the final presentation of the explanation. For this purpose, we perform an empirical study to explore these pitfalls along with their unintended consequences and propose remedies to mitigate their effects.

[1]  M. Yamada,et al.  GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks , 2020, IEEE Transactions on Knowledge and Data Engineering.

[2]  Bernd Bischl,et al.  Interpretable Machine Learning - A Brief History, State-of-the-Art and Challenges , 2020, PKDD/ECML Workshops.

[3]  Bo Zong,et al.  Parameterized Explainer for Graph Neural Network , 2020, NeurIPS.

[4]  Kang Li,et al.  On Explainability of Graph Neural Networks via Subgraph Explorations , 2021, International Conference on Machine Learning.

[5]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[6]  Marko Bohanec,et al.  Perturbation-Based Explanations of Prediction Models , 2018, Human and Machine Learning.

[7]  Jure Leskovec,et al.  GNNExplainer: Generating Explanations for Graph Neural Networks , 2019, NeurIPS.

[8]  Shuiwang Ji,et al.  XGNN: Towards Model-Level Explanations of Graph Neural Networks , 2020, KDD.

[9]  Takaya Saito,et al.  The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets , 2015, PloS one.

[10]  M. de Rijke,et al.  CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks , 2021, International Conference on Artificial Intelligence and Statistics.

[11]  Freddy Lécué,et al.  On The Role of Knowledge Graphs in Explainable AI , 2020, PROFILES/SEMEX@ISWC.

[12]  Zhiyuan Liu,et al.  Graph Neural Networks: A Review of Methods and Applications , 2018, AI Open.

[13]  Shuiwang Ji,et al.  Explainability in Graph Neural Networks: A Taxonomic Survey , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Jure Leskovec,et al.  How Powerful are Graph Neural Networks? , 2018, ICLR.

[15]  Francisco Herrera,et al.  Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI , 2020, Inf. Fusion.