├── README.md └── bytopics.md /README.md: -------------------------------------------------------------------------------- 1 | # awesome-graph-explainability-papers 2 | Papers about the explainability of GNNs 3 | 4 | ### Surveys 5 | 1. [ACM computing survey 25] **Explaining the Explainers in Graph Neural Networks: a Comparative Study** [paper](https://dl.acm.org/doi/pdf/10.1145/3696444) 6 | 2. [Proceedings of the IEEE 24] **Trustworthy Graph Neural Networks: Aspects, Methods and Trends** [paper](https://arxiv.org/abs/2205.07424) 7 | 3. [Preprint 24] **Graph-Based Explainable AI: A Comprehensive Survey** [paper](https://hal.science/hal-04660442/) 8 | 4. [Arixv 23] **A Survey on Explainability of Graph Neural Networks** [paper](https://arxiv.org/abs/2306.01958) 9 | 5. [ACM computing survey] **A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges** [paper](https://dl.acm.org/doi/abs/10.1145/3618105) 10 | 6. [TPAMI 22]**Explainability in graph neural networks: A taxonomic survey**. *Yuan Hao, Yu Haiyang, Gui Shurui, Ji Shuiwang*. [paper](https://arxiv.org/pdf/2012.15445.pdf) 11 | 7. [Arxiv 22]**A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metrics** [paper](https://arxiv.org/pdf/2207.12599.pdf) 12 | 8. [Arxiv 22] **A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection** [paper](https://arxiv.org/abs/2205.10014) 13 | 9. [Big Data 2022]**A Survey of Explainable Graph Neural Networks for Cyber Malware Analysis** [paper](https://ieeexplore.ieee.org/abstract/document/10020943) 14 | 10. [Machine Intelligence Research 24] **A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability**[paper](https://arxiv.org/abs/2204.08570) 15 | 11. [Book 23] **Generative Explanation for Graph Neural Network: Methods and Evaluation** [paper](http://sites.computer.org/debull/A23june/p64.pdf) 16 | 17 | ### Platforms 18 | 1. **PyTorch Geometric** [[Document]](https://pytorch-geometric.readthedocs.io/en/latest/tutorial/explain.html) [[Blog]](https://medium.com/@pytorch_geometric/graph-machine-learning-explainability-with-pyg-ff13cffc23c2) 19 | 2. **DIG: A Turnkey Library for Diving into Graph Deep Learning Research** [paper](https://www.jmlr.org/papers/v22/21-0343.html) [Code](https://github.com/divelab/DIG) 20 | 2. **GraphXAI: Evaluating Explainability for Graph Neural Networks** [paper](https://arxiv.org/abs/2208.09339v2) [Code](https://github.com/mims-harvard/graphxai) 21 | 3. **GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks** [paper](https://arxiv.org/abs/2206.09677) [Code](https://github.com/graphframex/graphframex) 22 | 4. **GNNExplainer and PGExplainer** [paper](https://openreview.net/forum?id=8JHrucviUf) [Code](https://github.com/LarsHoldijk/RE-ParameterizedExplainerForGraphNeuralNetworks) 23 | 5. **BAGEL: A Benchmark for Assessing Graph Neural Network Explanations** [[paper]](https://arxiv.org/abs/2206.13983)[Code](https://github.com/mandeep-rathee/bagel-benchmark) 24 | 25 | 26 | ### Most Influential Papers selected by [Cogdl](https://github.com/THUDM/cogdl/blob/master/gnn_papers.md#explainability 27 | 1. **Explainability in graph neural networks: A taxonomic survey**. *Yuan Hao, Yu Haiyang, Gui Shurui, Ji Shuiwang*. ARXIV 2020. [paper](https://arxiv.org/pdf/2012.15445.pdf) 28 | 2. **Gnnexplainer: Generating explanations for graph neural networks**. *Ying Rex, Bourgeois Dylan, You Jiaxuan, Zitnik Marinka, Leskovec Jure*. NeurIPS 2019. [paper](https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7138248/) [code](https://github.com/RexYing/gnn-model-explainer) 29 | 3. **Explainability methods for graph convolutional neural networks**. *Pope Phillip E, Kolouri Soheil, Rostami Mohammad, Martin Charles E, Hoffmann Heiko*. CVPR 2019.[paper](https://openaccess.thecvf.com/content_CVPR_2019/papers/Pope_Explainability_Methods_for_Graph_Convolutional_Neural_Networks_CVPR_2019_paper.pdf) 30 | 4. **Parameterized Explainer for Graph Neural Network**. *Luo Dongsheng, Cheng Wei, Xu Dongkuan, Yu Wenchao, Zong Bo, Chen Haifeng, Zhang Xiang*. NeurIPS 2020. [paper](https://arxiv.org/abs/2011.04573) [code](https://github.com/flyingdoog/PGExplainer) 31 | 5. **Xgnn: Towards model-level explanations of graph neural networks**. *Yuan Hao, Tang Jiliang, Hu Xia, Ji Shuiwang*. KDD 2020. [paper](https://dl.acm.org/doi/pdf/10.1145/3394486.3403085). 32 | 6. **Evaluating Attribution for Graph Neural Networks**. *Sanchez-Lengeling Benjamin, Wei Jennifer, Lee Brian, Reif Emily, Wang Peter, Qian Wesley, McCloskey Kevin, Colwell Lucy, Wiltschko Alexander*. NeurIPS 2020.[paper](https://proceedings.neurips.cc/paper/2020/file/417fbbf2e9d5a28a855a11894b2e795a-Paper.pdf) 33 | 7. **PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks**. *Vu Minh, Thai My T.*. NeurIPS 2020.[paper](https://arxiv.org/pdf/2010.05788.pdf) 34 | 8. **Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks**. *Federico Baldassarre and Kevin Smith and Josephine Sullivan and Hossein Azizpour*. ECCV 2020.[paper](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123730613.pdf) 35 | 9. **GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media**. *Lu, Yi-Ju and Li, Cheng-Te*. ACL 2020.[paper](https://arxiv.org/pdf/2004.11648.pdf) 36 | 10. **On Explainability of Graph Neural Networks via Subgraph Explorations**. *Yuan Hao, Yu Haiyang, Wang Jie, Li Kang, Ji Shuiwang*. ICML 2021.[paper](https://arxiv.org/pdf/2102.05152.pdf) 37 | 38 | ### Year 2025 39 | 1. [ICLR 25] **Exact Computation of Any-Order Shapley Interactions for Graph Neural Networks**[[paper]](https://openreview.net/forum?id=9tKC0YM8sX) 40 | 2. [ICLR 25] **From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks**[[paper]](https://openreview.net/forum?id=KEUPk0wXXe) 41 | 3. [ICLR 25] **Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks** [[paper]](https://openreview.net/forum?id=iFK0xoceR0) 42 | 4. [ICLR 25] **Towards Explaining the Power of Constant-depth Graph Neural Networks for Linear Programming** [[paper]](https://openreview.net/forum?id=INow59Vurm) 43 | 5. [ICLR 25] **Explanations of GNN on Evolving Graphs via Axiomatic Layer edges** [[paper]](https://openreview.net/forum?id=pXN8T5RwNN) 44 | 6. [ICLR 25] **MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation** [[paper]](https://openreview.net/forum?id=vue9P1Ypk6) 45 | 7. [AAAI 25] **Higher Order Structures For Graph Explanations** [[paper]](https://arxiv.org/abs/2406.03253) 46 | 8. [AAAI 25] **Self-Explainable Graph Transformer for Link Sign Prediction**[[paper]](https://arxiv.org/abs/2408.08754) 47 | 9. [AAAI 25] **Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint**[[paper]](https://arxiv.org/abs/2406.04612) 48 | 10. [AAAI 25] **Graph Segmentation and Contrastive Enhanced Explainer for Graph Neural Networks** [[paper]](https://ojs.aaai.org/index.php/AAAI/article/view/35440) 49 | 11. [TKDD 25] **DyExplainer: Explainable Dynamic Graph Neural Networks** [[paper]](https://arxiv.org/abs/2310.16375) 50 | 12. [Arxiv 25.05] **Dual Explanations via Subgraph Matching for Malware Detection** [[paper]](https://arxiv.org/pdf/2504.20904) 51 | 13. [Arxiv 25.04] **On the Consistency of GNN Explanations for Malware Detection** [[paper]](https://arxiv.org/pdf/2504.16316) 52 | 14. [Arxiv 25.01] **Watermarking Graph Neural Networks via Explanations for Ownership Protection** [[paper]](https://arxiv.org/abs/2501.05614) 53 | 15. [Arxiv 25.01] **Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection** [[paper]](https://arxiv.org/abs/2501.03432) 54 | 16. [ACM Computing Surveys] **Can Graph Neural Networks be Adequately Explained? A Survey** [[paper]](https://dl.acm.org/doi/abs/10.1145/3711122) 55 | 17. [IEEE TNSRE] **Finding Neural Biomarkers for Motor Learning and Rehabilitation using an Explainable Graph Neural Network** [[paper]](https://ieeexplore.ieee.org/abstract/document/10843258) 56 | 18. [Springer FCS] **Learning from shortcut: a shortcut-guided approach for explainable graph learning** [[paper]](https://link.springer.com/article/10.1007/s11704-024-40452-4) 57 | 19. [NN] **Local interpretable spammer detection model with multi-head graph channel attention network** [[paper]](https://www.sciencedirect.com/science/article/pii/S0893608024009985) 58 | 20. [ Applied Intelligence ] **KnowGNN: a knowledge-aware and structure-sensitive model-level explainer for graph neural networks** [[paper]](https://link.springer.com/article/10.1007/s10489-024-06034-4) 59 | 60 | 61 | ### Year 2024 62 | 1. [NeurIPS 24] **RegExplainer: Generating Explanations for Graph Neural Networks in Regression Task** [[paper]](https://arxiv.org/abs/2307.07840) 63 | 2. [NeurIPS 24] **GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules**[[paper]](https://nips.cc/virtual/2024/poster/94172) 64 | 3. [ICML 24] **Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks**[[paper]](https://arxiv.org/abs/2402.02036) 65 | 4. [ICML 24] **Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks** [[paper]](https://arxiv.org/abs/2401.08627) 66 | 5. [ICML 24] **Graph Neural Network Explanations are Fragile** [[paper]](https://arxiv.org/pdf/2406.03193) 67 | 6. [ICML 24] **How Interpretable Are Interpretable Graph Neural Networks?** [[paper]](https://arxiv.org/abs/2406.07955) 68 | 7. [ICML 24] **Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation**[[paper]](https://arxiv.org/abs/2402.08845) 69 | 8. [ICML 24] **Explaining Graph Neural Networks via Structure-aware Interaction Index** [[paper]](https://icml.cc/virtual/2024/poster/34550) 70 | 9. [ICML 24] **EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time** [[paper]](https://arxiv.org/abs/2405.01762) 71 | 10. [ICLR 24] **GraphChef: Decision-Tree Recipes to Explain Graph Neural Networks** [[paper]](https://openreview.net/forum?id=IjMUGuUmBI) 72 | 11. [ICLR 24] **GOAt: Explaining Graph Neural Networks via Graph Output Attribution** [[paper]](https://openreview.net/forum?id=2Q8TZWAHv4) 73 | 12. [ICLR 24] **Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks** [[paper]](https://openreview.net/forum?id=up6hr4hIQH) 74 | 13. [ICLR 24] **GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking** [[paper]](https://arxiv.org/abs/2310.01794) 75 | 14. [ICLR 24] **UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models** [[paper]](https://openreview.net/forum?id=0j9ZDzMPqr) 76 | 15. [TPAMI 24] **Towards Inductive and Efficient Explanations for Graph Neural Networks**[[paper]](https://ieeexplore.ieee.org/abstract/document/10423141) 77 | 20. [Openreview 24] **Robust Graph Attention for Graph Adversarial Attacks: An Information Bottleneck Inspired Approach**[[paper]](https://openreview.net/forum?id=lTL4t68BNc) 78 | 21. [Openreview 24] **AIMing for Explainability in GNNs**[[paper]]([https://openreview.net/forum?id=lTL4t68BNc](https://openreview.net/forum?id=KZII3faAs2)) 79 | 23. [Openreview 24] **Graph Distributional Analytics: Enhancing GNN Explainability through Scalable Embedding and Distribution Analysis**[[paper]](https://openreview.net/forum?id=Fzz8acgC6X) 80 | 25. [Openreview 24] **Watermarking Graph Neural Networks Via Explanations For Ownership Protection**[[paper]](https://openreview.net/forum?id=EgP6IEyfYJ) 81 | 26. [Openreview 24] **Explainable Graph Representation Learning via Graph Pattern Analysis** [[paper]](https://openreview.net/forum?id=hXJrQWIoR3) 82 | 28. [Openreview 24] **Robust Heterogeneous Graph Neural Network Explainer with Graph Information Bottleneck** [[paper]](https://openreview.net/forum?id=IMWYNVBHob) 83 | 29. [Openreview 24] **A Hierarchical Language Model Design For Interpretable Graph Reasoning** [[paper]](https://openreview.net/forum?id=DRSSLefryd) 84 | 30. [Openreview 24] **The GECo algorithm for Graph Neural Networks Explanation** [[paper]](https://openreview.net/forum?id=sTQC4TeYo1) 85 | 31. [Openreview 24] **On Explaining Equivariant Graph Networks via Improved Relevance Propagation** [[paper]](https://openreview.net/forum?id=YkMg8sB8AH) 86 | 32. [Openreview 24] **SIG: Self-Interpretable Graph Neural Network for Continuous-time Dynamic Graphs** [[paper]](https://openreview.net/forum?id=j0KjevdhkH) 87 | 33. [Openreview 24] **Interpretable and Adaptive Graph Contrastive Learning with Information Sharing for Biomedical Link Prediction** [[paper]](https://openreview.net/forum?id=GlgD9o9bl4) 88 | 35. [Openreview 24] **TAGExplainer: Narrating Graph Explanations for Text-Attributed Graph Learning Models** [[paper]](https://openreview.net/forum?id=VWBYDo5NaM) 89 | 37. [Openreview 24] **TreeX: Generating Global Graphical GNN Explanations via Critical Subtree Extraction** [[paper]](https://openreview.net/forum?id=zSUXo1nkqR) 90 | 38. [TMLR 24] **InduCE: Inductive Counterfactual Explanations for Graph Neural Networks** [[paper]](https://openreview.net/forum?id=RZPN8cgqST) 91 | 39. [PLDI 24] **PL4XGL: A Programming Language Approach to Explainable Graph Learning**[[paper]](https://dl.acm.org/doi/10.1145/3656464) 92 | 40. [Usenix Security 24] **INSIGHT: Attacking Industry-Adopted Learning Resilient Logic Locking Techniques Using Explainable Graph Neural Network**[[paper]](https://www.usenix.org/conference/usenixsecurity24/presentation/mankali) 93 | 41. [SIGMOD 24]**View-based Explanations for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2401.02086) 94 | 42. [ACM SIGMOD Record] **The Road to Explainable Graph Neural Networks** [[paper]](https://dl.acm.org/doi/abs/10.1145/3703922.3703930) 95 | 43. [Thesis UCLA] **Explainable Artificial Intelligence for Graph Data**[[paper]](https://escholarship.org/uc/item/6bf1g6dc) 96 | 44. [Thesis UVA] **Algorithmic Fairness in Graph Machine Learning: Explanation, Optimization, and Certification**[[paper]](https://www.proquest.com/docview/3083271574) 97 | 45. [KDD 24] **SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learning**[[paper]](https://arxiv.org/abs/2406.11389) 98 | 46. [KDD 24] **Self-Explainable Temporal Graph Networks based on Graph Information Bottleneck**[[paper]](https://arxiv.org/abs/2406.13214) 99 | 47. [KDD 24] **Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks**[[paper]](https://arxiv.org/abs/2407.01979) 100 | 48. [ICDE 24] **Generating Robust Counterfactual Witnesses for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2404.19519) 101 | 49. [ICDE 24] **SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networks**[[paper]](https://arxiv.org/abs/2407.11358) 102 | 50. [ICSE 24] **Coca: Improving and Explaining Graph Neural Network-Based Vulnerability Detection Systems**[[paper]](https://arxiv.org/abs/2401.14886) 103 | 51. [AAAI 24] **Generating Diagnostic and Actionable Explanations for Fair Graph Neural Networks** [[paper]](https://ojs.aaai.org/index.php/AAAI/article/view/30168) 104 | 52. [AAAI 24] **Stratifed GNN Explanations through Sufficient Expansion**[[paper]](https://ojs.aaai.org/index.php/AAAI/article/view/29180) 105 | 53. [AAAI 24] **Factorized Explainer for Graph Neural Networks**[[paper]](https://arxiv.org/abs/2312.05596) 106 | 54. [AAAI 24] **Self-Interpretable Graph Learning with Sufficient and Necessary Explanations** 107 | 55. [AAAI 24] **Explainable Origin-Destination Crowd Flow Interpolation via Variational Multi-Modal Recurrent Graph Auto-Encoder** [[paper]](https://ojs.aaai.org/index.php/AAAI/article/view/28796) 108 | 13. [AISTATS 24] **Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process** [[paper]](https://proceedings.mlr.press/v238/kong24a.html) 109 | 14. [WWW 24] **Game-theoretic Counterfactual Explanation for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2402.06030) 110 | 15. [WWW 24] **EXGC: Bridging Efficiency and Explainability in Graph Condensation**[[paper]](https://arxiv.org/abs/2402.05962) 111 | 16. [WWW 24] **Adversarial Mask Explainer for Graph Neural Networks** [[paper]](https://dl.acm.org/doi/abs/10.1145/3589334.3645608) 112 | 17. [WWW 24] **Globally Interpretable Graph Learning via Distribution Matching**[[paper]](https://arxiv.org/abs/2306.10447) 113 | 18. [WWW 24] **GNNShap: Scalable and Accurate GNN Explanation using Shapley Values** [[paper]](https://dl.acm.org/doi/abs/10.1145/3589334.3645599) 114 | 19. [LOG 24] **xAI-Drop: Don't Use What You Cannot Explain**[[paper]](https://openreview.net/forum?id=adlpuqQD8Q) 115 | 20. [LOG 24] **MOSE-GNN: A Motif-Based Self-Explaining Graph Neural Network for Molecular Property Prediction** [[paper]](https://openreview.net/forum?id=nD1a6hSLhO) 116 | 22. [TNNLS 24] **BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck** [[paper]](https://arxiv.org/abs/2205.03612) 117 | 23. [TKDE 24] **On Regularization for Explaining Graph Neural Networks: An Information Theory Perspective** [[paper]](https://openreview.net/forum?id=5rX7M4wa2R_) 118 | 24. [TKDD 24] **Towards Prototype-Based Self-Explainable Graph Neural Network** [[paper]](https://dl.acm.org/doi/10.1145/3689647) 119 | 25. [TKDD 24] **Efficient GNN Explanation via Learning Removal-based Attribution** [[paper]](https://dl.acm.org/doi/10.1145/3685678) 120 | 26. [TAI 24] **Learning Counterfactual Explanation of Graph Neural Networks via Generative Flow Network**[[paper]](https://ieeexplore.ieee.org/document/10496445) 121 | 27. [TAI 24] **Traffexplainer: A Framework towards GNN-based Interpretable Traffic Prediction** [[paper]](https://ieeexplore.ieee.org/abstract/document/10680338) 122 | 28. [TMC 24] **HGExplainer: Heterogeneous Graph Explainer for IoT Device Identification**[[paper]](https://ieeexplore.ieee.org/abstract/document/10736553) 123 | 29. [IEEE TMI 24] **Multi-Modal Diagnosis of Alzheimer’s Disease using Interpretable Graph Convolutional Networks**[[paper]](https://ieeexplore.ieee.org/abstract/document/10606492) 124 | 30. [IEEE IoT 24] **EXVul: Toward Effective and Explainable Vulnerability Detection for IoT Devices**[[paper]](https://ieeexplore.ieee.org/document/10479158) 125 | 31. [IEEE Transactions on Fuzzy Systems] **Towards Embedding Ambiguity-Sensitive Graph Neural Network Explainability** [[paper]](https://ieeexplore.ieee.org/abstract/document/10696966) 126 | 32. [IEEE JBHI] **Interpretable Dynamic Directed Graph Convolutional Network for Multi-Relational Prediction of Missense Mutation and Drug Response**[[paper]](https://ieeexplore.ieee.org/abstract/document/10721576) 127 | 33. [IDEAL 2024] **Causal Explanation of Graph Neural Networks**[[paper]](https://link.springer.com/chapter/10.1007/978-3-031-77731-8_26) 128 | 34. [BIBM 24] **Seizure Onset Zone Localization Method based on GNN Explanation** [[paper]](https://ieeexplore.ieee.org/abstract/document/10821860) 129 | 35. [BIBM 24] **DDTExplainer: Mining Drug-Disease Therapeutic Mechanisms based on GNN Explainability** [[paper]](https://ieeexplore.ieee.org/abstract/document/10822060) 130 | 36. [CIKM 24] **EDGE: Evaluation Framework for Logical vs. Subgraph Explanations for Node Classifiers on Knowledge Graphs**[[paper]](https://dl.acm.org/doi/abs/10.1145/3627673.3679904) 131 | 37. [ECML/PKDD 24] **Towards Few-shot Self-explaining Graph Neural Networks**[[paper]](https://arxiv.org/abs/2408.07340) 132 | 38. [SDM 24] **XGExplainer: Robust Evaluation-based Explanation for Graph Neural Networks**[[paper]](https://epubs.siam.org/doi/abs/10.1137/1.9781611978032.8) 133 | 23. [DASFAA 24] **Multi-objective Graph Neural Network Explanatory Model with Local and Global Information Preservation**[[paper]](https://link.springer.com/chapter/10.1007/978-981-97-5572-1_20) 134 | 28. [ISSTA 2024] **Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanation** [[paper]](https://arxiv.org/abs/2404.15687) 135 | 29. [KBS 24] **Shapley-based graph explanation in embedding space**[[paper]](https://www.sciencedirect.com/science/article/abs/pii/S0950705124008785?via%3Dihub) 136 | 30. [KBS 24] **GEAR: Learning graph neural network explainer via adjusting gradients**[[paper]](https://www.sciencedirect.com/science/article/abs/pii/S0950705124010025) 137 | 31. [IEEE TNSM 24] **Ensemble Graph Attention Networks for Cellular Network Analytics: From Model Creation to Explainability**[[paper]](https://ieeexplore.ieee.org/abstract/document/10622099) 138 | 32. [IEEE TNSE 24] **GAXG: A Global and Self-adaptive Optimal Graph Topology Generation Framework for Explaining Graph Neural Networks**[[paper]](https://ieeexplore.ieee.org/abstract/document/10614894) 139 | 33. [IEEE TETCI 24] **GF-LRP: A Method for Explaining Predictions Made by Variational Graph Auto-Encoders**[[paper]](https://ieeexplore.ieee.org/abstract/document/10586750) 140 | 34. [AAAI workshop] **Semi-Supervised Graph Representation Learning with Human-centric Explanation for Predicting Fatty Liver Disease**[[paper]](https://arxiv.org/abs/2403.02786) 141 | 35. [xAI 24] **Global Concept Explanations for Graphs by Contrastive Learning** [[paper]](https://arxiv.org/abs/2404.16532) 142 | 36. [Arxiv 24.12] **BetaExplainer: A Probabilistic Method to Explain Graph Neural Networks**[[paper]](https://arxiv.org/abs/2412.11964) 143 | 37. [Arxiv 24.12] **GISExplainer: On Explainability of Graph Neural Networks via Game-theoretic Interaction Subgraphs** [[paper]](https://arxiv.org/abs/2409.15698) 144 | 38. [Arxiv 24.12] **Interpreting GNN-based IDS Detections Using Provenance Graph Structural Features** [[paper]](https://arxiv.org/abs/2306.00934) 145 | 39. [Arxiv 24.12] **eXpath: Explaining Knowledge Graph Link Prediction with Ontological Closed Path Rules**[[paper]](https://arxiv.org/abs/2412.04846) 146 | 40. [Arxiv 24.12] **On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approach** [[paper]](https://arxiv.org/abs/2212.07056) 147 | 41. [Arxiv 24.11] **Rethinking Node Representation Interpretation through Relation Coherence**[[paper]](https://arxiv.org/abs/2411.00653) 148 | 42. [Arxiv 24.11] **MBExplainer: Multilevel bandit-based explanations for downstream models with augmented graph embeddings** [[paper]](https://arxiv.org/abs/2411.00287) 149 | 43. [Arxiv 24.11] **Securing GNNs: Explanation-Based Identification of Backdoored Training Graphs**[[paper]](https://arxiv.org/abs/2403.18136) 150 | 44. [Preprint 24.11] **Chiseling the Graph: An Edge-Sculpting Method for Explaining Graph Neural Networks** [[paper]](https://www.researchsquare.com/article/rs-5414037/v1) 151 | 45. [Preprint 24.10] **Reliable and Faithful Generative Explainers for Graph Neural Networks**[[paper]](https://www.preprints.org/manuscript/202410.1718) 152 | 46. [Arxiv 24.10] **Explaining Hypergraph Neural Networks: From Local Explanations to Global Concepts**[[paper]](https://arxiv.org/abs/2410.07764) 153 | 47. [Arxiv 24.10] **Explainable Graph Neural Networks Under Fire** [[paper]](https://arxiv.org/abs/2406.06417) 154 | 48. [Arxiv 24.09] **GINTRIP: Interpretable Temporal Graph Regression using Information bottleneck and Prototype-based method** [[paper]](https://arxiv.org/abs/2409.10996) 155 | 49. [Arxiv 24.09] **PAGE: Parametric Generative Explainer for Graph Neural Network** [[paper]](https://arxiv.org/abs/2408.14042) 156 | 50. [Preprint 24.08] **CIDER: Counterfactual-Invariant Diffusion-based GNN Explainer for Causal Subgraph Inference**[[paper]](https://www.researchsquare.com/article/rs-4814778/v1) 157 | 51. [Arxiv 24.07] **LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation**[[paper]](https://arxiv.org/abs/2407.15351) 158 | 52. [Arxiv 24.07] **Explaining Graph Neural Networks for Node Similarity on Graphs**[[paper]](https://arxiv.org/abs/2407.07639) 159 | 41. [Arxiv 24.07] **SLInterpreter: An Exploratory and Iterative Human-AI Collaborative System for GNN-based Synthetic Lethal Prediction**[[paper]](https://arxiv.org/abs/2407.14770) 160 | 42. [Arxiv 24.07] **Graph Neural Network Causal Explanation via Neural Causal Models**[[paper]](https://arxiv.org/abs/2407.09378) 161 | 43. [Arxiv 24.06] **GNNAnatomy: Systematic Generation and Evaluation of Multi-Level Explanations for Graph Neural Networks**[[paper]](https://arxiv.org/abs/2406.04548) 162 | 44. [Arxiv 24.06] **On GNN explanability with activation rules**[[paper]](https://arxiv.org/abs/2406.11594) 163 | 46. [Arxiv 24.05] **SIG: Efficient Self-Interpretable Graph Neural Network for Continuous-time Dynamic Graphs**[[paper]](https://arxiv.org/abs/2405.19062) 164 | 47. [Arxiv 24.06] **L2XGNN: Learning to Explain Graph Neural Networks** [[paper]](https://arxiv.org/pdf/2209.14402.pdf) 165 | 48. [Arxiv 24.06] **Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learning**[[paper]](https://arxiv.org/abs/2407.00849) 166 | 50. [Arxiv 24.06] **Explainable AI Security: Exploring Robustness of Graph Neural Networks to Adversarial Attacks** [[paper]](https://arxiv.org/abs/2406.13920) 167 | 51. [Arxiv 24.06] **Robust Ante-hoc Graph Explainer using Bilevel Optimization** [[paper]](https://arxiv.org/abs/2305.15745) 168 | 52. [Arxiv 24.06] **Perks and Pitfalls of Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs** [[paper]](https://arxiv.org/abs/2406.15156) 169 | 53. [Arxiv 24.05] **Utilizing Description Logics for Global Explanations of Heterogeneous Graph Neural Networks** [[paper]](https://arxiv.org/abs/2405.12654) 170 | 54. [Arxiv 24.05] **Detecting Complex Multi-step Attacks with Explainable Graph Neural Network** [[paper]](https://arxiv.org/abs/2405.11335) 171 | 55. [Arxiv 24.05] **SynHING: Synthetic Heterogeneous Information Network Generation for Graph Learning and Explanation**[[paper]](https://arxiv.org/abs/2401.04133) 172 | 56. [Arxiv 24.05] **PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2210.17159) 173 | 57. [Arxiv 24.05] **Evaluating Neighbor Explainability for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2311.08118) 174 | 58. [Preprint 24.05] **Explainable Graph Neural Networks: An Application to Open Statistics Knowledge Graphs for Estimating House Prices** [[paper]](https://www.preprints.org/manuscript/202405.0037/v1) 175 | 59. [Arxiv 24.04] **Superior Polymeric Gas Separation Membrane Designed by Explainable Graph Machine Learning** [[paper]](https://arxiv.org/abs/2404.10903) 176 | 60. [Arxiv 24.04] **Improving the interpretability of GNN predictions through conformal-based graph sparsification** [[paper]](https://arxiv.org/abs/2404.12356) 177 | 61. [Arxiv 24.03] **GreeDy and CoDy: Counterfactual Explainers for Dynamic Graph**[[paper]](https://arxiv.org/abs/2403.16846) 178 | 62. [Arxiv 24.03] **Explainable Graph Neural Networks for Observation Impact Analysis in Atmospheric State Estimation**[[paper]](https://arxiv.org/abs/2403.17384) 179 | 64. [Arixv 24.03] **Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanations**[[paper]](https://arxiv.org/abs/2403.07849) 180 | 65. [Arxiv 24.02] **PAC Learnability under Explanation-Preserving Graph Perturbations**[[paper]](https://arxiv.org/abs/2402.05039) 181 | 66. [Arxiv 24.02] **Explainable Global Wildfire Prediction Models using Graph Neural Networks**[[paper]](https://arxiv.org/abs/2402.07152) 182 | 67. [Arxiv 24.02] **Incorporating Retrieval-based Causal Learning with Information Bottlenecks for Interpretable Graph Neural Networks**[[paper]](https://arxiv.org/abs/2402.04710) 183 | 68. [Arxiv 24.01] **On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions**[[paper]](https://arxiv.org/abs/2401.00633) 184 | 69. [ASP=DAC 24] **LIPSTICK: Corruptibility-Aware and Explainable Graph Neural Network-based Oracle-Less Attack on Logic Locking**[[paper]](https://arxiv.org/abs/2402.04235) 185 | 70. [Biorxiv 24] **Community-aware explanations in knowledge graphs with XP-GNN**[[paper]](https://www.biorxiv.org/content/10.1101/2024.01.21.576302v1.abstract) 186 | 71. [ISCV 24] **Adaptive Subgraph Feature Extraction for Explainable Multi-Modal Learning**[[paper]](https://ieeexplore.ieee.org/document/10620106/) 187 | 72. [IJCNN 24] **Explanations for Graph Neural Networks using A Game-theoretic Value**[[paper]](https://ieeexplore.ieee.org/document/10650495) 188 | 73. [AIxIA 2024] **Relating Explanations with the Inductive Biases of Deep Graph Networks** [[paper]](https://link.springer.com/chapter/10.1007/978-3-031-80607-0_14) 189 | 74. [Neurocomputing] **GeoExplainer: Interpreting Graph Convolutional Networks with geometric masking**[[paper]](https://www.sciencedirect.com/science/article/abs/pii/S0925231224011640?via%3Dihub) 190 | 75. [Technologies] **Explainable Graph Neural Networks: An Application to Open Statistics Knowledge Graphs for Estimating House Prices**[[paper]](https://www.mdpi.com/2227-7080/12/8/128) 191 | 76. [Reliab. Eng. Syst. Saf.] **Causal intervention graph neural network for fault diagnosis of complex industrial processes**[[paper]](https://ieeexplore.ieee.org/document/10620106/) 192 | 77. [Frontiers in big data] **Global explanation supervision for Graph Neural Networks**[[paper]](https://www.semanticscholar.org/reader/b6d6dda72e1d31e4b05e59909128cfccf4a835fb) 193 | 78. [Information and Software Technology] **Graph-based explainable vulnerability prediction**[[paper]](https://www.sciencedirect.com/science/article/pii/S095058492400171X?via%3Dihub) 194 | 79. [Information Systems] **Heterogeneous graph neural networks for fraud detection and explanation in supply chain finance**[[paper]](https://www.sciencedirect.com/science/article/abs/pii/S0306437923001710?via%3Dihub) 195 | 80. [Information Procs. & Mana.] **Towards explaining graph neural networks via preserving prediction ranking and structural dependency**[[paper]](https://www.sciencedirect.com/science/article/pii/S0306457323003084) 196 | 81. [Applied Energy] **Explainable Spatio-Temporal Graph Neural Networks for multi-site photovoltaic energy production** [[paper]](https://www.sciencedirect.com/science/article/pii/S0306261923015155) 197 | 82. [PAKDD 24] **Random Mask Perturbation Based Explainable Method of Graph Neural Networks** [[paper]](https://link.springer.com/chapter/10.1007/978-981-97-2259-4_2) 198 | 83. [Computational Materials Science] **Graph isomorphism network for materials property prediction along with explainability analysis**[[paper]](https://www.sciencedirect.com/science/article/pii/S0927025623006134) 199 | 84. [NN 24] **Explanatory subgraph attacks against Graph Neural Networks**[[paper]](https://www.sciencedirect.com/science/article/pii/S0893608024000030) 200 | 85. [NN 24] **GRAM: An interpretable approach for graph anomaly detection using gradient attention maps**[[paper]](https://www.sciencedirect.com/science/article/pii/S0893608024003873) 201 | 86. [Neural Networks 24] **CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis** [[paper]](https://arxiv.org/abs/2301.01642) 202 | 87. [NeuroImage 24] **BPI-GNN: Interpretable brain network-based psychiatric diagnosis and subtyping**[[paper]](https://www.sciencedirect.com/science/article/pii/S1053811924000892) 203 | 88. [PAKDD 24] **Toward Interpretable Graph Classification via Concept-Focused Structural Correspondence** [[paper]](https://link.springer.com/chapter/10.1007/978-981-97-2650-9_2) 204 | 89. [ICPR 24] **Interpretable Deep Graph-Level Clustering: A Prototype-Based Approach** [[paper]](https://link.springer.com/chapter/10.1007/978-3-031-78128-5_8) 205 | 90. [MedRxiv 24] **An Interpretable Population Graph Network to Identify Rapid Progression of Alzheimer’s Disease Using UK Biobank**[[paper]](https://www.medrxiv.org/content/10.1101/2024.03.27.24304966v1) 206 | 91. [IEEE TDSC 24] **TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support** [[paper]](https://arxiv.org/pdf/2306.13339.pdf) 207 | 92. [IEEE Transactions] **IEEE Transactions on Computational Social Systems**[[paper]](https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6570650) 208 | 93. [Journal of Physics] **Explainer on GNN-based segmentation networks**[[paper]](https://iopscience.iop.org/article/10.1088/1742-6596/2711/1/012009/meta) 209 | 94. [Energy and AI] **Electricity demand forecasting at distribution and household levels using explainable causal graph neural network** [[paper]](https://www.sciencedirect.com/science/article/pii/S266654682400034X) 210 | 95. [HI-AI@KDD 24] **Interpretable Graph Model with Prototype-Based Graph Information Bottleneck** [[paper]](https://human-interpretable-ai.github.io/assets/pdf/4_Interpretable_Graph_Model_wi.pdf) 211 | 96. [Neurosymbolic Artificial Intelligence] **Towards Semantic Understanding of GNN Layers embedding with Functional-Semantic Activation Mapping** [[paper]](https://neurosymbolic-ai-journal.com/system/files/nai-paper-803.pdf) 212 | 97. [NeSy 2024] **Towards Understanding Graph Neural Networks: Functional-Semantic Activation Mapping**[[paper]](https://link.springer.com/chapter/10.1007/978-3-031-71170-1_11) 213 | 98. [Thesis 24] **Explainable and physics-guided graph deep learning for air pollution modelling** [[paper]](https://cris.vub.be/ws/portalfiles/portal/117178225/RodrigoBonet_Esther_thesis.pdf) 214 | 99. [Thesis 24] **Influence of molecular structures on graph neural network explainers’ performance**[[paper]](https://repository.tudelft.nl/file/File_03ae5c75-cc17-42c1-a593-1c82d2593c67?preview=1) 215 | 216 | 217 | 218 | 219 | 220 | 221 | 222 | 223 | ### Year 2023 224 | 1. [NeurIPS 23] **Interpretable Graph Networks Formulate Universal Algebra Conjectures**[[paper]](https://arxiv.org/abs/2307.11688) 225 | 2. [NeurIPS 23] **SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanation** [[paper]](https://openreview.net/forum?id=kBBsj9KRgh) 226 | 3. [NeurIPS 23] **Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks**[[paper]](https://openreview.net/forum?id=enfx8HM4Rp) 227 | 4. [NeurIPS 23] **D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion** [[paper]](https://arxiv.org/abs/2310.19321) 228 | 5. [NeurIPS 23] **TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery** [[paper]](https://arxiv.org/abs/2310.19324) 229 | 6. [NeurIPS 23] **V-InFoR: A Robust Graph Neural Networks Explainer for Structurally Corrupted Graphs** [[paper]](https://openreview.net/forum?id=CtXXOaxDw7) 230 | 7. [NeurIPS 23] **Towards Self-Interpretable Graph-Level Anomaly Detection** [[paper]](https://arxiv.org/abs/2310.16520) 231 | 8. [NeurIPS 23] **Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis** [[paper]](https://openreview.net/forum?id=eD534mPhAg) 232 | 9. [NeurIPS 23] **Interpretable Prototype-based Graph Information Bottleneck** [[paper]](https://arxiv.org/abs/2310.19906) 233 | 10. [ICML 23] **Rethinking Explaining Graph Neural Networks via Non-parametric Subgraph Matching** [[paper]](https://openreview.net/forum?id=MocsSAUKlk) 234 | 11. [ICML 23] **Relevant Walk Search for Explaining Graph Neural Networks** [[paper]](https://openreview.net/forum?id=BDYIci7bVs) 235 | 12. [ICML 23] **Towards Understanding the Generalization of Graph Neural Networks** [[paper]](https://openreview.net/pdf?id=BhMyLk0YNy) 236 | 13. [ICLR 23] **GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks** [[paper]](https://arxiv.org/pdf/2209.07924.pdf) 237 | 14. [ICLR 23] **Global Explainability of GNNs via Logic Combination of Learned Concepts** [[paper]](https://openreview.net/forum?id=OTbRTIY4YS) 238 | 15. [ICLR 23] **Explaining Temporal Graph Models through an Explorer-Navigator Framework** [[paper]](https://openreview.net/forum?id=BR_ZhvcYbGJ) 239 | 16. [ICLR 23] **DAG Matters! GFlowNets Enhanced Explainer for Graph Neural Networks** [[paper]](https://openreview.net/forum?id=jgmuRzM-sb6) 240 | 17. [ICLR 23] **Interpretable Geometric Deep Learning via Learnable Randomness Injection** [[paper]](https://arxiv.org/abs/2210.16966) 241 | 18. [ICLR 23] **A Differential Geometric View and Explainability of GNN on Evolving Graphs** [[paper]](https://openreview.net/forum?id=lRdhvzMpVYV) 242 | 19. [KDD 23] **MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation** [[paper]](https://arxiv.org/abs/2307.07832) 243 | 20. [KDD 23] **Counterfactual Learning on Heterogeneous Graphs with Greedy Perturbation** [[paper]](https://repository.kaust.edu.sa/handle/10754/693484) 244 | 21. [KDD 23] **Empower Post-hoc Graph Explanations with Information Bottleneck: A Pre-training and Fine-tuning Perspective**[[paper]](https://dl.acm.org/doi/10.1145/3580305.3599330) 245 | 22. [KDD 23] **Less is More: SlimG for Accurate, Robust, and Interpretable Graph Mining.**[[paper]](https://dl.acm.org/doi/10.1145/3580305.3599413) 246 | 23. [KDD 23] **Shift-Robust Molecular Relational Learning with Causal Substructure** [[paper]](https://dl.acm.org/doi/abs/10.1145/3580305.3599437) 247 | 24. [AAAI 23] **Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis** [[paper]](https://arxiv.org/abs/2208.10609) 248 | 25. [AAAI 23] **On the Limit of Explaining Black-box Temporal Graph Neural Networks** [[paper]](https://arxiv.org/abs/2212.00952) 249 | 26. [AAAI 23] **Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network** [[paper]](https://ojs.aaai.org/index.php/AAAI/article/download/26040/25812) 250 | 27. [AAAI 23] **Interpretable Chirality-Aware Graph Neural Network for Quantitative Structure Activity Relationship Modeling in Drug Discovery** [[paper]](https://openreview.net/forum?id=W2OStztdMhc) 251 | 28. [VLDB 23] **HENCE-X: Toward Heterogeneity-agnostic Multi-level Explainability for Deep Graph Networks** [[paper]](https://www.vldb.org/pvldb/vol16/p2990-lv.pdf) 252 | 29. [VLDB 23] **On Data-Aware Global Explainability of Graph Neural Networks** [[paper]](https://www.vldb.org/pvldb/vol16/p3447-lv.pdf) 253 | 30. [AISTATS 23] **Distill n' Explain: explaining graph neural networks using simple surrogates** [[Paper]](https://arxiv.org/abs/2303.10139) 254 | 31. [AISTATS 23] **Probing Graph Representations** [[paper]](https://proceedings.mlr.press/v206/akhondzadeh23a/akhondzadeh23a.pdf) 255 | 32. [ICDE 23] **INGREX: An Interactive Explanation Framework for Graph Neural Networks**[[paper]](https://arxiv.org/pdf/2211.01548.pdf) 256 | 33. [ICDE 23] **Jointly Attacking Graph Neural Network and its Explanations** [[paper]](https://arxiv.org/pdf/2108.03388.pdf) 257 | 34. [WWW 23]**PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Prediction** [[paper]](https://arxiv.org/pdf/2302.12465.pdf) 258 | 35. [ICDM 23] **Limitations of Perturbation-based Explanation Methods for Temporal Graph Neural Networks** 259 | 36. [ICDM 23] **Interpretable Subgraph Feature Extraction for Hyperlink Prediction**[[paper]](https://www.researchgate.net/publication/378000024_Interpretable_Subgraph_Feature_Extraction_for_Hyperlink_Prediction) 260 | 37. [WSDM 23]**Interpretable Research Interest Shift Detection with Temporal Heterogeneous Graphs** [[paper]](https://dl.acm.org/doi/pdf/10.1145/3539597.3570453) 261 | 38. [WSDM 23]**Cooperative Explanations of Graph Neural Networks** [[paper]](https://dl.acm.org/doi/pdf/10.1145/3539597.3570378) 262 | 39. [WSDM 23]**Towards Faithful and Consistent Explanations for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2205.13733) 263 | 40. [WSDM 23] **Global Counterfactual Explainer for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2210.11695) 264 | 41. [CIKM 23] **Explainable Spatio-Temporal Graph Neural Networks** [[paper]](https://dl.acm.org/doi/abs/10.1145/3583780.3614871) 265 | 42. [CIKM 23] **DuoGAT: Dual Time-oriented Graph Attention Networks for Accurate, Efficient and Explainable Anomaly Detection on Time-series.** [[paper]](https://dl.acm.org/doi/abs/10.1145/3583780.3614857) 266 | 43. [CIKM 23] **Heterogeneous Temporal Graph Neural Network Explainer** [[paper]](https://dl.acm.org/doi/abs/10.1145/3583780.3614909) 267 | 44. [CIKM 23] **ACGAN-GNNExplainer: Auxiliary Conditional Generative Explainer for Graph Neural Networks**[[paper]]() 268 | 45. [CIKM 23] **KG4Ex: An Explainable Knowledge Graph-Based Approach for Exercise Recommendation** [[paper]](https://dl.acm.org/doi/10.1145/3583780.3614943) 269 | 46. [ECML-PKDD 23] **ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learning** [[paper]](https://arxiv.org/abs/2307.01053) 270 | 47. [TPAMI 23] **FlowX: Towards Explainable Graph Neural Networks via Message Flows** [[paper]](https://arxiv.org/abs/2206.12987) 271 | 48. [TAI] **Prototype-based interpretable graph neural networks.** [[paper]](https://ieeexplore.ieee.org/document/9953541) 272 | 49. [TKDE 23] **Counterfactual Graph Learning for Anomaly Detection on Attributed Networks** [[paper]](https://ieeexplore.ieee.org/document/10056298) 273 | 50. [Scientific Data 23 ] **Evaluating explainability for graph neural networks** [[paper]](https://www.nature.com/articles/s41597-023-01974-x) 274 | 51. [Nature Communications 23] **Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking** [[paper]](https://www.nature.com/articles/s41467-023-38192-3) 275 | 52. [ACM Computing Surveys 23] **A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation** [[paper]](https://arxiv.org/abs/2210.12089) 276 | 53. [TIST 23] **Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment** [[paper]](https://arxiv.org/abs/2301.02791) 277 | 54. [Openreview 23] **STExplainer: Global Explainability of GNNs via Frequent SubTree Mining** [[paper]](https://openreview.net/forum?id=HgSfV6sGIn) 278 | 55. [GLFrontiers 23] **Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts** [[paper]](https://openreview.net/forum?id=wrqAn3AJA1) 279 | 56. [Openreview 23] **Iterative Graph Neural Network Enhancement Using Explanations** [[paper]](https://openreview.net/forum?id=qp0oVaFGm0) 280 | 58. [Openreview 23] **Interpretable and Convergent Graph Neural Network Layers at Scale** [[paper]](https://openreview.net/forum?id=uYTaVRkKvz) 281 | 60. [NeurIPS 2023 Workshop XAIA] **GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Networks Explanations** [[paper]](https://openreview.net/forum?id=88MalncLgU) 282 | 61. [NeurIPS 2023 Workshop XAIA] **On the Consistency of GNN Explainability Methods** [[paper]](https://openreview.net/forum?id=tiLZkab8TP) 283 | 65. [Arxiv 23] **Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation**[[paper]](https://arxiv.org/abs/2312.17301) 284 | 66. [AICS 23] **A subgraph interpretation generative model for knowledge graph link prediction based on uni-relation transformation** [[paper]](https://www.spiedigitallibrary.org/conference-proceedings-of-spie/12803/1280339/A-subgraph-interpretation-generative-model-for-knowledge-graph-link-prediction/10.1117/12.3009388.short?SSO=1) 285 | 67. [GUT 23] **Screening of normal endoscopic large bowel biopsies with interpretable graph learning: a retrospective study** [[paper]](https://gut.bmj.com/content/gutjnl/early/2023/05/11/gutjnl-2023-329512.full.pdf) 286 | 68. [PR 2023] **Towards self-explainable graph convolutional neural network with frequency adaptive inception** [[paper]](https://www.sciencedirect.com/science/article/abs/pii/S0031320323006891) 287 | 69. [MLG 2023] **Understanding how explainers work in graph neural networks** [[paper]](https://mlg-europe.github.io/papers/241.pdf) 288 | 70. [MLG 2023] **Graph Model Explainer Tool** [[paper]](https://www.mlgworkshop.org/2023/papers/MLG__KDD_2023_paper_5.pdf) 289 | 71. [Information Science 23] **Robust explanations for graph neural network with neuron explanation component** [[paper]](https://www.sciencedirect.com/science/article/pii/S0020025523013701) 290 | 72. [Recsys 23] **Explainable Graph Neural Network Recommenders; Challenges and Opportunities** [[paper]](https://dl.acm.org/doi/abs/10.1145/3604915.3608875) 291 | 73. [xAI 23] **Counterfactual Explanations for Graph Classification Through the Lenses of Density** [[paper]](https://arxiv.org/abs/2307.14849) 292 | 74. [XAI 23] **Evaluating Link Prediction Explanations for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2308.01682 293 | 75. [xAI 23] **XInsight: Revealing Model Insights for GNNs with Flow-based Explanations** [[paper]](https://arxiv.org/pdf/2306.04791.pdf) 294 | 76. [xAI 23] **Quantifying the Intrinsic Usefulness of Attributional Explanations for Graph Neural Networks with Artificial Simulatability Studies** [[paper]](https://arxiv.org/abs/2305.15961) 295 | 77. [xAI 23] **MEGAN: Multi Explanation Graph Attention Network** [[paper]](https://openreview.net/forum?id=H6LVUiHzYDE) 296 | 78. [XKDD 23] **Game Theoretic Explanations for Graph Neural Networks** [[paper]](http://xkdd2023.isti.cnr.it/papers/424.pdf) 297 | 79. [XKDD 23] **From Black Box to Glass Box: Evaluating Faithfulness of Process Predictions with GCNNs** [[paper]](http://xkdd2023.isti.cnr.it/papers/425.pdf) 298 | 80. [IJCNN 23] **MEGA: Explaining Graph Neural Networks with Network Motifs** [[paper]](https://doi.org/10.1109/IJCNN54540.2023.10191684) 299 | 81. [LOG Poster 23] **On the Robustness of Post-hoc GNN Explainers to Label Noise** [[paper]](https://arxiv.org/abs/2309.01706) 300 | 82. [LOG Poster 23] **How Faithful are Self-Explainable GNNs?** [[paper]](https://arxiv.org/abs/2308.15096) 301 | 84. [LOG Poster 23] **Explaining Link Predictions in Knowledge Graph Embedding Models with Influential Examples** [[paper]](https://arxiv.org/abs/2212.02651) 302 | 85. [Bioriv 23] **Building explainable graph neural network by sparse learning for the drug-protein binding prediction** [[paper]](https://www.biorxiv.org/content/10.1101/2023.08.28.555203v1.abstract) 303 | 86. [ICAID 2023] **Explanations for Graph Neural Networks via Layer Analysis.** [[paper]](https://www.atlantis-press.com/proceedings/icaid-23/125990065) 304 | 87. [ECAI 23] **XGBD: Explanation-Guided Graph Backdoor Detection** [[paper]](https://arxiv.org/abs/2308.04406) 305 | 88. [IEEE Transactions on Consumer Electronics 23] **Human Pose Prediction Using Interpretable Graph Convolutional Network for Smart Home** [[paper]](https://arxiv.org/abs/2308.04406) 306 | 89. [KBS 23] **KE-X: Towards subgraph explanations of knowledge graph embedding based on knowledge information gain** [[paper]](http://sites.computer.org/debull/A23june/A23JUNE-CD.pdf#page=64) 307 | 90. [ICML workshop 23] **Generating Global Factual and Counterfactual Explainer for Molecule under Domain Constraints** [[paper]](https://openreview.net/forum?id=qElXYQqxQh) 308 | 91. [Thesis 23] **Developing interpretable graph neural networks for high dimensional feature spaces** [[paper]](https://pub.tik.ee.ethz.ch/students/2022-HS/BA-2022-43.pdf) 309 | 92. [Thesis 23] **Evaluation of Explainability Methods on Single-Cell Classification Tasks Using Graph Neural Networks** [[paper]](https://www.semanticscholar.org/paper/Evaluation-of-Explainability-Methods-on-Single-Cell-Singh-Kobayashi/85f4aba430387a337ec3a4b2aa39bfc7361dea1f) 310 | 93. [Arxiv 23] **On the Interplay of Subset Selection and Informed Graph Neural Networks** [[paper]](https://arxiv.org/abs/2306.10066) 311 | 94. [ISSTA23] **Interpreters for GNN-Based Vulnerability Detection: Are We There Yet?** [[paper]](https://www.semanticscholar.org/paper/Interpreters-for-GNN-Based-Vulnerability-Detection%3A-Hu-Wang/6bb9c86483f212a631324ba9b47c344d419a428a) 312 | 95. [ICECAI23] **Improved GraphSVX for GNN Explanations Based on Cross Entropy** [[paper]](https://www.semanticscholar.org/paper/Improved-GraphSVX-for-GNN-Explanations-Based-on-Yu-Liang/b01c4f2c4d54723b590a828d4e1b4cdbfea5dad4) 313 | 96. [ICRA Workshop 23] **Towards Semantic Interpretation and Validation of Graph Attention-based Explanations** [[paper]](https://openreview.net/forum?id=ymyQeqatQqQ) 314 | 97. [Arxiv 23] **Graph Neural Network based Log Anomaly Detection and Explanation** [[paper]](https://arxiv.org/abs/2307.00527) 315 | 99. [Thesis 23] **Interpretability of Graphical Models** [[paper]](https://search.proquest.com/openview/1e61b389a59936e319974be0e3fd1af5/1?pq-origsite=gscholar&cbl=18750&diss=y) 316 | 101. [Bioengineering 2023] **Personalized Explanations for Early Diagnosis of Alzheimer's Disease Using Explainable Graph Neural Networks with Population Graphs** [[paper]](https://www.mdpi.com/2306-5354/10/6/701) 317 | 102. [BDSC 2023] **MDC: An Interpretable GNNs Method Based on Node Motif Degree and Graph Diffusion Convolution** [[paper]] (https://link.springer.com/chapter/10.1007/978-981-99-3925-1_24) 318 | 104. [Information Science 2023] **Explainability techniques applied to road traffic forecasting using Graph Neural Network models** [[paper]](https://www.sciencedirect.com/science/article/pii/S0020025523009052) 319 | 107. [Arxiv 23.05] **EiX-GNN : Concept-level eigencentrality explainer for graph neural networks** [[paper]](https://arxiv.org/abs/2206.03491) 320 | 108. [Arxiv 23.04] **Cognitive Explainers of Graph Neural Networks Based on Medical Concepts** [[paper]](https://arxiv.org/abs/2201.07798) 321 | 109. [ICLR Tiny 23] **Message-passing selection: Towards interpretable GNNs for graph classification** [[paper]](https://openreview.net/forum?id=99Go96dla5y) 322 | 110. [ICLR Tiny 23] **Revisiting CounteRGAN for Counterfactual Explainability of Graphs** [[paper]](https://openreview.net/forum?id=d0m0Rl15q3g) 323 | 111. [MICCAI Workshop 23] **IA-GCN: Interpretable Attention based Graph Convolutional Network for Disease prediction** [[paper]](https://arxiv.org/pdf/2103.15587.pdf) 324 | 113. [GRADES & NDA'23] **A Demonstration of Interpretability Methods for Graph Neural Networks** [[paper]](https://homes.cs.aau.dk/~Arijit/Papers/gInterpreter_GRADES_NDA23.pdf) 325 | 114. [Arxiv 23] **Self-Explainable Graph Neural Networks for Link Prediction** [[paper]](https://arxiv.org/abs/2305.12578) 326 | 115. [Arxiv 23.02] **MotifExplainer: a Motif-based Graph Neural Network Explainer** [[paper]](https://arxiv.org/abs/2202.00519) 327 | 116. [ChemRxiv 23] **Interpreting Graph Neural Networks with Myerson Values for Cheminformatics Approaches** [[paper]](https://chemrxiv.org/engage/chemrxiv/article-details/6456c89707c3f0293753101d) 328 | 117. [Neural Networks 23] **Generating Post-hoc Explanations for Skip-gram-based Node Embeddings by Identifying Important Nodes with Bridgeness** [[paper]](https://arxiv.org/abs/2304.12036) 329 | 118. [ICASSP 23] **Towards a More Stable and General Subgraph Information Bottleneck** [[paper]](https://ieeexplore.ieee.org/document/10094812) 330 | 119. [ESANN 23] **Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability** [[Paper]](https://arxiv.org/abs/2304.07152) 331 | 120. [IEEE Access] **Generating Real-Time Explanations for GNNs via Multiple Specialty Learners and Online Knowledge Distillation** [[Paper]](https://ieeexplore.ieee.org/document/10107968) 332 | 121. [IEEE Access] **Providing Post-Hoc Explanation for Node Representation Learning Models Through Inductive Conformal Predictions** [[paper]](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10003193&tag=1) 333 | 122. [Journal of Software 23] **A Slice-level vulnerability detection and interpretation method based on graph neural network** [[paper]](http://www.jos.org.cn/josen/article/abstract/mr008) 334 | 123. [Automation in Construction 23] **Learning from explainable data-driven tunneling graphs: A spatio-temporal graph convolutional network for clogging detection** [[paper]](https://www.sciencedirect.com/science/article/pii/S0926580523000018) 335 | 124. [Briefings in Bioinformatics] **Predicting molecular properties based on the interpretable graph neural network with multistep focus mechanism** [[paper]](https://academic.oup.com/bib/advance-article/doi/10.1093/bib/bbac534/6918752) 336 | 125. [Briefings in Bioinformatics] **Identification of vital chemical information via visualization of graph neural networks** [[paper]](https://academic.oup.com/bib/article/24/1/bbac577/6936421) 337 | 126. [Bioinformatics 23] **Explainable Multilayer Graph Neural Network for Cancer Gene Prediction** [[paper]](https://arxiv.org/pdf/2301.08831.pdf) 338 | 127. [ICLR Workshop 23] **GCI: A Graph Concept Interpretation Framework** [[paper]](https://arxiv.org/abs/2302.04899) 339 | 128. [Arxiv 23] **Structural Explanations for Graph Neural Networks using HSIC** [[paper]](https://arxiv.org/abs/2302.02139) 340 | 129. [Internet of Things 23] **XG-BoT: An Explainable Deep Graph Neural Network for Botnet Detection and Forensics** [[paper]](https://arxiv.org/abs/2207.09088) 341 | 130. [JOS23] **A Generic Explaining & Locating Method for Malware Detection based on Graph Neural Networks** [[paper]](https://www.jos.org.cn/josen/article/abstract/7123) 342 | 131. [IJCNN 23] **GRAPHSHAP: Explaining Identity-Aware Graph Classifiers Through the Language of Motifs** [[paper]](https://arxiv.org/abs/2202.08815) 343 | 141. [Arxiv 23.01] **Explainability in subgraphs-enhanced Graph Neural Networks** [[paper]](https://arxiv.org/abs/2209.07926) 344 | 345 | ### Year 2022 346 | 1. [NeurIPS 22] **GStarX:Explaining Graph-level Predictions with Communication Structure-Aware Cooperative Games** [[paper]](https://openreview.net/pdf?id=Qry8exovcNA) 347 | 2. [NeurIPS 22] **Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure** [[paper]](https://arxiv.org/abs/2209.14107) 348 | 3. [NeurIPS 22] **Task-Agnostic Graph Neural Explanations** [[paper]](https://openreview.net/pdf?id=NQrx8EYMboO) 349 | 4. [NeurIPS 22] **CLEAR: Generative Counterfactual Explanations on Graphs**[[paper]](https://arxiv.org/abs/2210.08443) 350 | 5. [ICML 22] **Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism** [[paper]](https://arxiv.org/abs/2201.12987v1) 351 | 6. [ICLR 22] **DEGREE: Decomposition Based Explanation for Graph Neural Networks** [[paper]](https://openreview.net/pdf?id=Ve0Wth3ptT_) 352 | 7. [ICLR 22] **Explainable GNN-Based Models over Knowledge Graphs** [[paper]](https://openreview.net/attachment?id=CrCvGNHAIrz&name=pdf) 353 | 8. [ICLR 22] **Discovering Invariant Rationales for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2201.12872) 354 | 9. [KDD 22] **On Structural Explanation of Bias in Graph Neural Networks** [[paper]](https://arxiv.org/abs/2206.12104) 355 | 10. [KDD 22] **Causal Attention for Interpretable and Generalizable Graph Classification** [[paper]](https://arxiv.org/abs/2112.15089) 356 | 10. [CVPR 22] **OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks** [[paper]](https://wanyu-lin.github.io/assets/publications/wanyu-cvpr2022.pdf) 357 | 81. [CVPR 22] **Improving Subgraph Recognition with Variational Graph Information Bottleneck** [[paper]](https://arxiv.org/abs/2112.09899) 358 | 12. [AISTATS 22] **Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods** [[paper]](https://arxiv.org/abs/2106.09078) 359 | 13. [AISTATS 22] **CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2102.03322) 360 | 14. [TPAMI 22] **Differentially Private Graph Neural Networks for Whole-Graph Classification** [[paper]](https://arxiv.org/abs/2212.03806) 361 | 15. [TPAMI 22] **Reinforced Causal Explainer for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2204.11028) 362 | 17. [VLDB 22] **xFraud: Explainable Fraud Transaction Detection on Heterogeneous Graphs** [[paper]](https://arxiv.org/pdf/2011.12193.pdf) 363 | 18. [LOG 22]**GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2206.09677) 364 | 19. [LOG 22] **Towards Training GNNs using Explanation Directed Message Passing** [[paper]](https://arxiv.org/abs/2211.16731) 365 | 20. [The Webconf 22] **Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning** [[paper]](https://arxiv.org/abs/2202.08816) 366 | 21. [AAAI 22] **Prototype-Based Explanations for Graph Neural Networks** [[paper]](https://www.aaai.org/AAAI22Papers/SA-00396-ShinY.pdf) 367 | 36. [AAAI 22] **KerGNNs: Interpretable Graph Neural Networks with Graph Kernels**[[paper]](https://arxiv.org/pdf/2201.00491.pdf) 368 | 37. [AAAI 22] **ProtGNN: Towards Self-Explaining Graph Neural Networks** [[paper]](https://arxiv.org/abs/2112.00911) 369 | 23. [IEEE Big Data 22] **Trade less Accuracy for Fairness and Trade-off Explanation for GNN** [[paper]](https://ieeexplore.ieee.org/abstract/document/10020318) 370 | 28. [CIKM 22] **GRETEL: A unified framework for Graph Counterfactual Explanation Evaluation** [[paper]](https://arxiv.org/abs/2206.02957) 371 | 29. [CIKM 22] **GRETEL: Graph Counterfactual Explanation Evaluation Framework**[[paper]](https://dl.acm.org/doi/abs/10.1145/3511808.3557608) 372 | 30. [CIKM 22] **A Model-Centric Explainer for Graph Neural Network based Node Classification** [[paper]](https://dl.acm.org/doi/10.1145/3511808.3557535) 373 | 31. [IJCAI 22] **What Does My GNN Really Capture? On Exploring Internal GNN Representations** [[paper]](https://hal.archives-ouvertes.fr/hal-03700710/) 374 | 32. [ECML PKDD 22] **Improving the quality of rule-based GNN explanations** [[paper]](https://kdd.isti.cnr.it/xkdd2022/papers/XKDD_2022_paper_2436.pdf) 375 | 33. [MICCAI 22] **Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis** [[paper]](https://arxiv.org/abs/2207.00813) 376 | 34. [MICCAI 22] **Sparse Interpretation of Graph Convolutional Networks for Multi-modal Diagnosis of Alzheimer’s Disease** [[paper]](https://link.springer.com/chapter/10.1007/978-3-031-16452-1_45) 377 | 38. [EuroS&P 22] **Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysis** [[paper]](https://ieeexplore.ieee.org/abstract/document/9797387?casa_token=1AvRK3S4eJQAAAAA:8PXcOA8iU1ketRMdu6YVMBMcfZKjF7MIVujPpHTpjdc2O9r1cvUg8usfRiOYZ5Fe-MKJi4Y) 378 | 39. [INFOCOM 22] **Interpretability Evaluation of Botnet Detection Model based on Graph Neural Network** [[paper]](https://ieeexplore.ieee.org/document/9798287) 379 | 40. [GLOBECOM 22] **Shapley Explainer - An Interpretation Method for GNNs Used in SDN** [[paper]](https://ieeexplore.ieee.org/abstract/document/10001460) 380 | 41. [GLOBECOM 22] **An Explainer for Temporal Graph Neural Networks** [[paper]]([https://arxiv.org/pdf/2209.00807.pdf]) 381 | 42. [TKDE 22] **Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks** [[paper]](https://arxiv.org/abs/2105.08621) 382 | 43. [TNNLS 22] **Interpretable Graph Reservoir Computing With the Temporal Pattern Attention** [[paper]](https://ieeexplore.ieee.org/abstract/document/10003110) 383 | 44. [TNNLS22] **A Meta-Learning Approach for Training Explainable Graph Neural Networks** [[paper]](https://ieeexplore.ieee.org/abstract/document/9772740) 384 | 45. [TNNLS 22] **Explaining Deep Graph Networks via Input Perturbation** [[paper]](https://pubmed.ncbi.nlm.nih.gov/35446771/) 385 | 63. [TNNLS 22] **A Meta-Learning Approach for Training Explainable Graph Neural Network** [[paper]](https://arxiv.org/pdf/2109.09426.pdf) 386 | 47. [DMKD 22] **On GNN explanability with activation patterns** [[paper]](https://hal.archives-ouvertes.fr/hal-03367714/file/hal.pdf) 387 | 48. [KBS 22] **EGNN: Constructing explainable graph neural networks via knowledge distillation** [[paper]](https://www.sciencedirect.com/science/article/pii/S0950705122001289?via%3Dihub) 388 | 49. [XKDD 22] **GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations** [[paper]](https://arxiv.org/abs/2208.04222) 389 | 50. [AI 22] **Are Graph Neural Network Explainers Robust to Graph Noises?** [[paper]](https://link.springer.com/chapter/10.1007/978-3-031-22695-3_12) 390 | 52. [BRACIS 22] **ConveXplainer for Graph Neural Networks** [[paper]](https://link.springer.com/chapter/10.1007/978-3-031-21689-3_41) 391 | 53. [GLB 22] **An Explainable AI Library for Benchmarking Graph Explainers** [[paper]](https://graph-learning-benchmarks.github.io/assets/papers/glb2022/An_Explainable_AI_Library_for_Benchmarking_Graph_Explainers.pdf) 392 | 54. [DASFAA 22] **On Global Explainability of Graph Neural Networks** [[paper]](https://link.springer.com/chapter/10.1007/978-3-031-00123-9_52) 393 | 55. [ISBI 22] **Interpretable Graph Convolutional Network Of Multi-Modality Brain Imaging For Alzheimer’s Disease Diagnosis** [[paper]](https://ieeexplore.ieee.org/abstract/document/9761449?casa_token=w3IlSZNlKwcAAAAA:Xvh04eK29bZtbkRq5Eg3jUZURS3qs1k3AA1bhnnN2kKWmIjBnh7alAiy98zBgsHFtvFQqV0IYA) 394 | 56. [Bioinformatics] **GNN-SubNet: disease subnetwork detection with explainable Graph Neural Networks** [[paper]](https://academic.oup.com/bioinformatics/article/38/Supplement_2/ii120/6702000?login=false) 395 | 57. [Medical Imaging 2022] **Phenotype guided interpretable graph convolutional network analysis of fMRI data reveals changing brain connectivity during adolescence** [[paper]](https://www.semanticscholar.org/paper/Phenotype-guided-interpretable-graph-convolutional-Orlichenko-Qu/d05adc7c772780be4b99a169441696017d49c6ed) 396 | 83. [NeuroComputing 22] **Perturb more, trap more: Understanding behaviors of graph neural networks** [[paper]](https://www.sciencedirect.com/science/article/pii/S0925231222004404?casa_token=6KLu9elyyLMAAAAA:hM0eGpfSnLxF0V8fZJdoDE3hkalzK2yccBJl3X9KN-Btu_xDSZmmbORIfkYdK5rgjTr7MReeFxc) 397 | 84. [DSN 22] **CFGExplainer: Explaining Graph Neural Network-Based Malware Classification from Control Flow Graphs** [[paper]](http://www.cs.binghamton.edu/~ghyan/papers/dsn22.pdf) 398 | 118. [IEEE Access 22] **Providing Node-level Local Explanation for node2vec through Reinforcement Learning** [[paper]](https://mlog-workshop.github.io/papers/MLoG%20Providing%20Node-level%20Local%20Explanation%20for%20node2vec%20through%20Reinforcement%20Learning.pdf) 399 | 119. [Patterns 22] **Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction** [[paper]](https://arxiv.org/pdf/2107.04119.pdf) 400 | 121. [IEEE Access 22] **Providing Post-Hoc Explanation for Node Representation Learning Models Through Inductive Conformal Predictions** [[paper]](https://ieeexplore.ieee.org/abstract/document/10003193) 401 | 122. [IEEE 22] **Explaining Graph Neural Networks With Topology-Aware Node Selection: Application in Air Quality Inference** [[paper]](https://ieeexplore.ieee.org/document/9801665) 402 | 123. [BioRxiv 22] **GNN-SubNet: disease subnetwork detection with explainable Graph Neural Networks** [[paper]](https://www.biorxiv.org/content/10.1101/2022.01.12.475995v1) 403 | 124. [IEEE Robotics and Automation Letters 22] **Efficient and Interpretable Robot Manipulation with Graph Neural Networks** [[paper]](https://arxiv.org/pdf/2102.13177.pdf) 404 | 125. [Arxiv 22] **Deconfounding to Explanation Evaluation in Graph Neural Networks** [[paper]](https://arxiv.org/abs/2201.08802) 405 | 126. [ICCPR 22] **GANExplainer: GAN-based Graph Neural Networks Explainer** [[paper]](https://arxiv.org/abs/2301.00012) 406 | 129. [Arxiv 22] **Exploring Explainability Methods for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2211.01770) 407 | 132. [Arxiv 22] **Toward Multiple Specialty Learners for Explaining GNNs via Online Knowledge Distillation** [[paper]](https://arxiv.org/abs/2210.11094) 408 | 134. [Openreview 23] **TGP: Explainable Temporal Graph Neural Networks for Personalized Recommendation** [[paper]](https://openreview.net/forum?id=EGobBwPc1J-) 409 | 139. [Arxiv 22] **PGX: A Multi-level GNN Explanation Framework Based on Separate Knowledge Distillation Processes** [[paper]](https://arxiv.org/abs/2208.03075) 410 | 142. [Arxiv 22] **Defending Against Backdoor Attack on Graph Neural Network by Explainability** [[paper]](https://arxiv.org/pdf/2209.02902.pdf) 411 | 144. [Arxiv 22] **Explaining Dynamic Graph Neural Networks via Relevance Back-propagation** [[paper]](https://arxiv.org/abs/2207.11175) 412 | 147. [Arxiv 22] **Faithful Explanations for Deep Graph Models** [[paper]](https://arxiv.org/abs/2205.11850) 413 | 148. [Arxiv 22] **Towards Explanation for Unsupervised Graph-Level Representation Learning** [[paper]](https://arxiv.org/abs/2205.09934) 414 | 149. [Arxiv 22] **BAGEL: A Benchmark for Assessing Graph Neural Network Explanations** [[paper]](https://arxiv.org/abs/2206.13983) 415 | 152. [Arxiv 22] **Explainability in Graph Neural Networks: An Experimental Survey** [[paper]](https://arxiv.org/abs/2203.09258) 416 | 153. [IEEE TSIPN 22] **Explainability and Graph Learning from Social Interactions** [[paper]](https://arxiv.org/pdf/2203.07494.pdf) 417 | 418 | 419 | 420 | ### Year 2021 421 | 1. [NeurIPS 21] **SALKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning** [[paper]](https://arxiv.org/pdf/2104.08793.pdf) 422 | 2. [NeurIPS 2021] **Reinforcement Learning Enhanced Explainer for Graph Neural Networks** [[paper]](http://recmind.cn/papers/explainer_nips21.pdf) 423 | 3. [NeurIPS 2021] **Towards Multi-Grained Explainability for Graph Neural Networks** [[paper]](http://staff.ustc.edu.cn/~hexn/papers/nips21-explain-gnn.pdf) 424 | 21. [NeurIPS 2021] **Robust Counterfactual Explanations on Graph Neural Networks** [[paper]](https://arxiv.org/abs/2107.04086) 425 | 22. [ICML 2021] **On Explainability of Graph Neural Networks via Subgraph Explorations**[[paper]](https://arxiv.org/abs/2102.05152) 426 | 32. [ICML 2021] **Generative Causal Explanations for Graph Neural Networks**[[paper]](https://arxiv.org/abs/2104.06643) 427 | 33. [ICML 2021] **Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity**[[paper]](https://arxiv.org/abs/2105.04854) 428 | 34. [ICML 2021] **Automated Graph Representation Learning with Hyperparameter Importance Explanation**[[paper]](http://proceedings.mlr.press/v139/wang21f/wang21f.pdf) 429 | 26. [ICLR 21] **Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs** [[paper]](https://openreview.net/forum?id=pGIHq1m7PU) 430 | 27. [ICLR 2021] **Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking**[[paper]](https://arxiv.org/abs/2010.00577) 431 | 52. [ICLR 2021] **Graph Information Bottleneck for Subgraph Recognition** [[paper]](https://arxiv.org/pdf/2010.05563.pdf) 432 | 53. [KDD 2021] **When Comparing to Ground Truth is Wrong: On Evaluating GNN Explanation Methods**[[paper]](https://dl.acm.org/doi/abs/10.1145/3447548.3467283) 433 | 54. [KDD 2021] **Counterfactual Graphs for Explainable Classification of Brain Networks** [[paper]](https://arxiv.org/abs/2106.08640) 434 | 27. [CVPR 2021] **Quantifying Explainers of Graph Neural Networks in Computational Pathology**.[[paper]](https://arxiv.org/pdf/2011.12646.pdf) 435 | 40. [NAACL 2021] **Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph Network**. [[paper]](https://aclanthology.org/2021.naacl-main.156.pdf) 436 | 28. [AAAI 2021] **Motif-Driven Contrastive Learning of Graph Representations** [[paper]](https://arxiv.org/pdf/2012.12533.pdf) 437 | 56. [TPAMI 21] **Higher-Order Explanations of Graph Neural Networks via Relevant Walks** [[paper]](https://ieeexplore.ieee.org/document/9547794) 438 | 57. [WWW 2021] **Interpreting and Unifying Graph Neural Networks with An Optimization Framework** [[paper]](https://arxiv.org/abs/2101.11859) 439 | 59. [Genome medicine 21] **Explaining decisions of Graph Convolutional Neural Networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer** [[paper]](https://www.semanticscholar.org/paper/Explaining-decisions-of-Graph-Convolutional-Neural-Chereda-Bleckmann/49a4e339182b2b304304c8837b09ce3e0951a616) 440 | 60. [IJCKG 21] **Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rules** [[paper]](https://arxiv.org/abs/2112.08589) 441 | 61. [RuleML+RR 21] **Combining Sub-Symbolic and Symbolic Methods for Explainability** [[paper]](https://arxiv.org/abs/2112.01844) 442 | 62. [PAKDD 21] **SCARLET: Explainable Attention based Graph Neural Network for Fake News spreader prediction** [[paper]](https://arxiv.org/abs/2102.04627) 443 | 63. [J. Chem. Inf. Model] **Coloring Molecules with Explainable Artificial Intelligence for Preclinical Relevance Assessment** [[paper]](https://pubs.acs.org/doi/abs/10.1021/acs.jcim.0c01344) 444 | 64. [BioRxiv 21] **APRILE: Exploring the Molecular Mechanisms of Drug Side Effects with Explainable Graph Neural Networks** [[paper]](https://www.biorxiv.org/content/10.1101/2021.07.02.450937v2.abstract) 445 | 65. [ISM 21] **Edge-Level Explanations for Graph Neural Networks by Extending Explainability Methods for Convolutional Neural Networks** [[paper]](https://arxiv.org/pdf/2111.00722.pdf) 446 | 67. [Arxiv 21] **Towards the Explanation of Graph Neural Networks in Digital Pathology with Information Flows** [[paper]](https://arxiv.org/abs/2112.09895) 447 | 68. [Arxiv 21] **SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods** [[paper]](https://arxiv.org/pdf/2106.08532.pdf) 448 | 69. [Arxiv 21] **Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation** [[paper]](https://arxiv.org/pdf/2103.13944.pdf) 449 | 70. [Arxiv 21] **Learnt Sparsification for Interpretable Graph Neural Networks** [[paper]](https://arxiv.org/pdf/2106.12920.pdf) 450 | 72. [ICML workshop 21] **GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks** [[paper]](https://arxiv.org/pdf/2107.11889.pdf) 451 | 74. [ICML workshop 21] **Reliable Graph Neural Network Explanations Through Adversarial Training** [[paper]](https://arxiv.org/pdf/2106.13427.pdf) 452 | 75. [ICML workshop 21] **Reimagining GNN Explanations with ideas from Tabular Data** [[paper]](https://arxiv.org/pdf/2106.12665.pdf) 453 | 76. [ICML workshop 21] **Towards Automated Evaluation of Explanations in Graph Neural Networks** [[paper]](https://arxiv.org/pdf/2106.11864.pdf) 454 | 79. [ICDM 2021] **GNES: Learning to Explain Graph Neural Networks** [[paper]](https://cs.emory.edu/~lzhao41/materials/papers/GNES.pdf) 455 | 80. [ICDM 2021] **GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs** [[paper]](https://arxiv.org/abs/2110.05598) 456 | 82. [ICDM 2021] **Multi-objective Explanations of GNN Predictions** [[paper]](https://arxiv.org/abs/2111.14651) 457 | 83. [CIKM 2021] **Towards Self-Explainable Graph Neural Network** [[paper]](https://arxiv.org/abs/2108.12055) 458 | 84. [ECML PKDD 2021] **GraphSVX: Shapley Value Explanations for Graph Neural Networks** [[paper]](https://arxiv.org/abs/2104.10482) 459 | 85. [WiseML 2021] **Explainability-based Backdoor Attacks Against Graph Neural Networks** [[paper]](https://dl.acm.org/doi/pdf/10.1145/3468218.3469046) 460 | 86. [IJCNN 21] **MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks** [[paper]](https://arxiv.org/pdf/2104.08060.pdf) 461 | 87. [ICCSA 2021] **Understanding Drug Abuse Social Network Using Weighted Graph Neural Networks Explainer** [[paper]](https://link.springer.com/chapter/10.1007%2F978-3-030-86970-0_5) 462 | 88. [NeSy 21] **A New Concept for Explaining Graph Neural Networks** [[paper]](http://ceur-ws.org/Vol-2986/paper1.pdf) 463 | 89. [Information Fusion 21] **Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI** [[paper]](https://www.sciencedirect.com/science/article/pii/S1566253521000142?via%3Dihub) 464 | 90. [Patterns 21] **hcga: Highly Comparative Graph Analysis for network phenotyping** [[paper]](https://www.biorxiv.org/content/10.1101/2020.09.25.312926v2) 465 | 466 | 467 | 468 | 469 | ### Year 2020 and Before 470 | 1. [NeurIPS 2020] **Parameterized Explainer for Graph Neural Network**.[[paper]](https://arxiv.org/abs/2011.04573) 471 | 2. [NeurIPS 2020] **PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks** [[paper]](https://arxiv.org/pdf/2010.05788.pdf) 472 | 3. [KDD 2020] **XGNN: Towards Model-Level Explanations of Graph Neural Networks** [[paper]](https://dl.acm.org/doi/10.1145/3394486.3403085) 473 | 4. [ACL 2020]**GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media**. [paper](https://arxiv.org/pdf/2004.11648.pdf) 474 | 5. [Arxiv 2020] **Graph Neural Networks Including Sparse Interpretability** [[paper]](https://arxiv.org/abs/2007.00119) 475 | 6. [NeurIPS Workshop 20] **Towards explainable message passing networks for predicting carbon dioxide adsorption in metal-organic frameworks** [[paper]](https://arxiv.org/abs/2012.03723) 476 | 7. [ICML workstop 2020] **Contrastive Graph Neural Network Explanation** [[paper]](https://arxiv.org/pdf/2010.13663.pdf) 477 | 8. [ICML workstop 2020] **Towards Explainable Graph Representations in Digital Pathology** [[paper]](https://arxiv.org/pdf/2007.00311.pdf) 478 | 9. [NeurIPS workshop 2020] **Explaining Deep Graph Networks with Molecular Counterfactuals** [[paper]](https://arxiv.org/pdf/2011.05134.pdf) 479 | 10. [DataMod 2020] **Exploring Graph-Based Neural Networks for Automatic Brain Tumor Segmentation"** [[paper]](https://link.springer.com/chapter/10.1007%2F978-3-030-70650-0_2) 480 | 12. [OpenReview 20] **A Framework For Differentiable Discovery Of Graph Algorithms** [[paper]](https://openreview.net/pdf?id=ueiBFzt7CiK) 481 | 13. [OpenReview 20] **Causal Screening to Interpret Graph Neural Networks** [[paper]](https://openreview.net/pdf?id=nzKv5vxZfge) 482 | 14. [Arxiv 20] **Understanding Graph Neural Networks from Graph Signal Denoising Perspectives** [[paper]](https://arxiv.org/pdf/2006.04386.pdf) 483 | 15. [Arxiv 20] **Understanding the Message Passing in Graph Neural Networks via Power Iteration** [[paper]](https://arxiv.org/pdf/2006.00144.pdf) 484 | 17. [IJCNN 20] **GCN-LRP explanation: exploring latent attention of graph convolutional networks**] [[paper]](https://ieeexplore.ieee.org/abstract/document/9207639) 485 | 18. [CD-MAKE 20] **Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification** [[paper]](https://arxiv.org/abs/2002.00514) 486 | 19. [ICDM 19] **Scalable Explanation of Inferences on Large Graphs**[[paper]](https://arxiv.org/abs/1908.06482) 487 | 488 | 489 | -------------------------------------------------------------------------------- /bytopics.md: -------------------------------------------------------------------------------- 1 | ## Health Informatics 2 | 1. [Bioengineering 2023] **Personalized Explanations for Early Diagnosis of Alzheimer's Disease Using Explainable Graph Neural Networks with Population Graphs** [[paper]](https://www.mdpi.com/2306-5354/10/6/701) 3 | 2. [Arixv 23] Explainable Multilayer Graph Neural Network for Cancer Gene Prediction [paper] 4 | 3. [Arxiv 23] **CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis** [[paper]](https://arxiv.org/abs/2301.01642) 5 | 4. [MICCAI 22] **Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis** [[paper]](https://arxiv.org/abs/2207.00813) 6 | 5. [MICCAI 22] **Sparse Interpretation of Graph Convolutional Networks for Multi-modal Diagnosis of Alzheimer’s Disease** [paper] 7 | 6. [Bioinformatics 22] GNN-SubNet: disease subnetwork detection with explainable Graph Neural Networks [paper] 8 | 7. [ISBI 22] **Interpretable Graph Convolutional Network Of Multi-Modality Brain Imaging For Alzheimer’s Disease Diagnosis** [[paper]](https://ieeexplore.ieee.org/abstract/document/9761449?casa_token=w3IlSZNlKwcAAAAA:Xvh04eK29bZtbkRq5Eg3jUZURS3qs1k3AA1bhnnN2kKWmIjBnh7alAiy98zBgsHFtvFQqV0IYA) 9 | 8. [Medical Imaging 2022] **Phenotype guided interpretable graph convolutional network analysis of fMRI data reveals changing brain connectivity during adolescence** [[paper]](https://www.semanticscholar.org/paper/Phenotype-guided-interpretable-graph-convolutional-Orlichenko-Qu/d05adc7c772780be4b99a169441696017d49c6ed) 10 | 9. [Arxiv 22] **BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck** [[paper]](https://arxiv.org/abs/2205.03612) 11 | 10. [KDD 2021] **Counterfactual Graphs for Explainable Classification of Brain Networks** [[paper]](https://arxiv.org/abs/2106.08640) 12 | 11. [ICML workshop 21] **BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis** [[paper]](https://arxiv.org/abs/2107.05097) 13 | 12. [Arxiv 21] IA-GCN: Interpretable Attention based Graph Convolutional Network for Disease prediction [paper] 14 | 15 | ## Counterfactual 16 | 1. [Arxiv 23] **Empowering Counterfactual Reasoning over Graph Neural Networks through Inductivity** [[paper]](https://arxiv.org/pdf/2306.04835.pdf) 17 | --------------------------------------------------------------------------------