Survey, Evaluation

Explainability in Graph Neural Networks: A Taxonomic Survey
– robustness  [Arxiv 22] A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability [paper]
 [Arxiv 22] Explainability in Graph Neural Networks: An Experimental Survey [paper]
 [AISTATS 22] Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods [paper]
 [The Webconf 22] Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning [paper]
 [KDD 2021] When Comparing to Ground Truth is Wrong: On Evaluating GNN Explanation Methods [paper]
 [2206.09677] GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks
 [2207.12599] A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metrics
Paper
 GraphLIME:Local Interpretable Model Explanations
 NIPS 19 GNNExplainer
 NIPS 20 PGMExplainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
 NIPS 20 Parameterized Explainer for Graph Neural Network
 KDD 20 XGNN
 ICML 21 [2102.05152] On Explainability of Graph Neural Networks via Subgraph Explorations
 Factorizable Graph Convolutional Networks
 NeurlPS 20 Submission: XAI for Graphs: Explaining Graph Neural Network Predictions by Identifying Relevant Walks
 CVPR 19: Explainability Methods for Graph Convolutional Neural Networks
 [IJCAI 22] What Does My GNN Really Capture? On Exploring Internal GNN Representations [paper]
 [TNNLS 22] Explaining Deep Graph Networks via Input Perturbation [paper]
 [KDD 22] On Structural Explanation of Bias in Graph Neural Networks [paper]
 [AISTATS 22] CFGNNExplainer: Counterfactual Explanations for Graph Neural Networks [paper]
 [NeuroComputing 22] Perturb more, trap more: Understanding behaviors of graph neural networks [paper]
 [DASFAA 22] On Glocal Explainability of Graph Neural Networks [paper]
 [AAAI 22] KerGNNs: Interpretable Graph Neural Networks with Graph Kernels [paper]
 [TPAMI 22] Reinforced Causal Explainer for Graph Neural Networks [paper]
 [CVPR 22] OrphicX: A CausalityInspired Latent Variable Model for Interpreting Graph Neural Networks [paper]
 [CVPR 22] Improving Subgraph Recognition with Variational Graph Information Bottleneck [paper]
 [Arxiv 22] GRAPHSHAP: Motifbased Explanations for Blackbox Graph Classifiers [paper]
 [KBS 22] EGNN: Constructing explainable graph neural networks via knowledge distillation [paper]
 [AAAI22] ProtGNN: Towards SelfExplaining Graph Neural Networks [paper]
 [ICML 22] Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism [paper]
 [OpenReview 21] Deconfounding to Explanation Evaluation in Graph Neural Networks [paper]
 [ICLR 22] Discovering Invariant Rationales for Graph Neural Networks [paper]
 [Arxiv 22] MotifExplainer: a Motifbased Graph Neural Network Explainer [paper]
 [TPAMI 21] HigherOrder Explanations of Graph Neural Networks via Relevant Walks [paper]
 [ICML 2021] Generative Causal Explanations for Graph Neural Networks [paper]
 [ICML workshop 21] Towards Automated Evaluation of Explanations in Graph Neural Networks [paper]
 [ICLR 2021] Graph Information Bottleneck for Subgraph Recognition [paper]
 [WWW 2021] Interpreting and Unifying Graph Neural Networks with An Optimization Framework [paper]
 [ICDM 2021] GNES: Learning to Explain Graph Neural Networks [paper]
 [ICDM 2021] GCNSE: Attention as Explainability for Node Classification in Dynamic Graphs [paper]
 [ICDM 2021] Multiobjective Explanations of GNN Predictions [paper]
 [CIKM 2021] Towards SelfExplainable Graph Neural Network [paper]
 [ECML PKDD 2021] GraphSVX: Shapley Value Explanations for Graph Neural Networks [paper]
 [NeSy 21] A New Concept for Explaining Graph Neural Networks [paper]
 [ICML workstop 2020] Contrastive Graph Neural Network Explanation [paper]
 [Arxiv 2020] Graph Neural Networks Including Sparse Interpretability [paper]
 [OpenReview 20] A Framework For Differentiable Discovery Of Graph Algorithms [paper]
 [OpenReview 20] Causal Screening to Interpret Graph Neural Networks [paper]
 [Arxiv 20] Understanding Graph Neural Networks from Graph Signal Denoising Perspectives [paper]
 [Arxiv 20] Understanding the Message Passing in Graph Neural Networks via Power Iteration [paper]
 [IJCNN 20] GCNLRP explanation: exploring latent attention of graph convolutional networks ] [paper]
Application
 [BioRxiv 22] GNNSubNet: disease subnetwork detection with explainable Graph Neural Networks [paper]
 [PAKDD 21] SCARLET: Explainable Attention based Graph Neural Network for Fake News spreader prediction [paper]
 [CVPR 2021] Quantifying Explainers of Graph Neural Networks in Computational Pathology .[paper]
 [ICML 2021] Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity [paper]
 [ICML workshop 21] GCExplainer: HumanintheLoop Conceptbased Explanations for Graph Neural Networks [paper]
 [ICML workshop 21] BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis [paper]
 [ICML workshop 21] Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction [paper]
 [KDD 2021] Counterfactual Graphs for Explainable Classification of Brain Networks [paper]
 [IJCNN 21] MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks [paper]