% Key papers for GNN explainability (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2019_gnnexplainer_58309,
  title = {{GNNExplainer: Generating Explanations for Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13964},
}

@inproceedings{neurips2020_parameterized_60568,
  title = {{Parameterized Explainer for Graph Neural Network}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17299},
}

@inproceedings{aaai2022_protgnn_2591,
  title = {{ProtGNN: Towards Self-Explaining Graph Neural Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/09127-protgnn-towards-self-explaining-graph-neural-networks/},
}

@inproceedings{iclr2020_what_29806,
  title = {{What Can Neural Networks Reason About?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rJxbJeHFPS},
}

@inproceedings{icml2021_on_39692,
  title = {{On Explainability of Graph Neural Networks via Subgraph Explorations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8873},
}

@inproceedings{neurips2020_evaluating_59805,
  title = {{Evaluating Attribution for Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17889},
}

@inproceedings{neurips2020_pgm_60559,
  title = {{PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17488},
}

@inproceedings{iclr2021_interpreting_30387,
  title = {{Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2852},
}

@inproceedings{neurips2021_robust_62350,
  title = {{Robust Counterfactual Explanations on Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26674},
}

@inproceedings{aaai2023_global_3778,
  title = {{Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26267},
}

@inproceedings{icml2021_generative_39385,
  title = {{Generative Causal Explanations for Graph Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8417},
}

@inproceedings{iclr2023_global_32499,
  title = {{Global Explainability of GNNs via Logic Combination of Learned Concepts}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11248},
}

@inproceedings{iclr2023_gnninterpreter_33254,
  title = {{GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10764},
}

@inproceedings{neurips2022_gstarx_64913,
  title = {{GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53592},
}

@inproceedings{aaai2024_factorized_5950,
  title = {{Factorized Explainer for Graph Neural Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29157},
}

@inproceedings{aaai2022_algorithmic_1725,
  title = {{Algorithmic Concept-Based Explainable Reasoning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/06685-algorithmic-concept-based-explainable-reasoning/},
}

@inproceedings{neurips2023_interpretable_69153,
  title = {{Interpretable Prototype-based Graph Information Bottleneck}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70730},
}

@inproceedings{iclr2022_degree_31349,
  title = {{DEGREE: Decomposition Based Explanation for Graph Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6059},
}

@inproceedings{neurips2024_relational_71324,
  title = {{Relational Concept Bottleneck Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95923},
}

@inproceedings{neurips2024_graphtrail_73268,
  title = {{GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94172},
}

@inproceedings{aaai2024_self_7287,
  title = {{Self-Interpretable Graph Learning with Sufficient and Necessary Explanations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29059},
}

@inproceedings{iclr2024_towards_35510,
  title = {{Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17563},
}

@inproceedings{neurips2024_regexplainer_73182,
  title = {{RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94251},
}

@inproceedings{iclr2024_gnnx_34567,
  title = {{GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18507},
}

@inproceedings{iclr2024_goat_33524,
  title = {{GOAt: Explaining Graph Neural Networks via Graph Output Attribution}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19551},
}

@inproceedings{neurips2025_on_76954,
  title = {{On Logic-based Self-Explainable Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=OtAiYPP6GA},
}

@inproceedings{iclr2025_mage_83940,
  title = {{MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/27883},
}

@inproceedings{aaai2025_higher_9446,
  title = {{Higher Order Structures for Graph Explanations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34260},
}

@inproceedings{icml2024_how_43902,
  title = {{How Interpretable Are Interpretable Graph Neural Networks?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34550},
}

@inproceedings{icml2024_eig_43981,
  title = {{EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34471},
}

@inproceedings{icml2024_graph_45453,
  title = {{Graph Neural Network Explanations are Fragile}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32998},
}

@inproceedings{neurips2025_sound_75383,
  title = {{Sound Logical Explanations for Mean Aggregation Graph Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=7TY89cqLfE},
}

@inproceedings{icml2024_generating_45376,
  title = {{Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33075},
}

@inproceedings{icml2025_beyond_48477,
  title = {{Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspective}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44141},
}

@inproceedings{icml2025_comrecgc_48683,
  title = {{COMRECGC: Global Graph Counterfactual Explainer through Common Recourse}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43939},
}

@inproceedings{neurips2025_robust_75089,
  title = {{Robust Explanations of Graph Neural Networks via Graph Curvatures}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=48L3BEtH8w},
}

@inproceedings{neurips2025_gnnxemplar_78440,
  title = {{GnnXemplar: Exemplars to Explanations - Natural Language Rules for Global GNN Interpretability}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=eafIjoZAHm},
}