amirtha255 / awesome-graph-explainability-papers

Papers about explainability of GNNs

awesome-graph-explainability-papers

Papers about explainability of GNNs

Surveys

1. Explainability in graph neural networks: A taxonomic survey. Yuan Hao, Yu Haiyang, Gui Shurui, Ji Shuiwang. ARXIV 2020. paper
2. A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metrics paper
3. Trustworthy Graph Neural Networks: Aspects, Methods and Trends paper
4. A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation [paper]
5. A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection paper
6. Explaining the Explainers in Graph Neural Networks: a Comparative Study paper

Platforms

1. GraphXAI: Evaluating Explainability for Graph Neural Networks paper Code
2. DIG: A Turnkey Library for Diving into Graph Deep Learning Research paper Code
3. GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks paper Code
4. GNNExplainer and PGExplainer paper Code

Most Influential Papers selected by [Cogdl](https://github.com/THUDM/cogdl/blob/master/gnn_papers.md#explainability

1. Explainability in graph neural networks: A taxonomic survey. Yuan Hao, Yu Haiyang, Gui Shurui, Ji Shuiwang. ARXIV 2020. paper
2. Gnnexplainer: Generating explanations for graph neural networks. Ying Rex, Bourgeois Dylan, You Jiaxuan, Zitnik Marinka, Leskovec Jure. NeurIPS 2019. paper code
3. Explainability methods for graph convolutional neural networks. Pope Phillip E, Kolouri Soheil, Rostami Mohammad, Martin Charles E, Hoffmann Heiko. CVPR 2019.paper
4. Parameterized Explainer for Graph Neural Network. Luo Dongsheng, Cheng Wei, Xu Dongkuan, Yu Wenchao, Zong Bo, Chen Haifeng, Zhang Xiang. NeurIPS 2020. paper code
5. Xgnn: Towards model-level explanations of graph neural networks. Yuan Hao, Tang Jiliang, Hu Xia, Ji Shuiwang. KDD 2020. paper.
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
7. PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks. Vu Minh, Thai My T.. NeurIPS 2020.paper
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
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
10. On Explainability of Graph Neural Networks via Subgraph Explorations. Yuan Hao, Yu Haiyang, Wang Jie, Li Kang, Ji Shuiwang. ICML 2021.paper

Year 2023

1. [ICDE 23] INGREX: An Interactive Explanation Framework for Graph Neural Networks[paper]
2. [WSDM 23]Towards Faithful and Consistent Explanations for Graph Neural Networks [paper]
3. [Arxiv 23] CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis [paper]

Year 2022

1. [TNNLS 22] Interpretable Graph Reservoir Computing With the Temporal Pattern Attention [paper]
2. [Briefings in Bioinformatics] Predicting molecular properties based on the interpretable graph neural network with multistep focus mechanism [paper]
3. [Arxiv 22] GANExplainer: GAN-based Graph Neural Networks Explainer [paper]
4. [Arxiv 22] On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approach [paper]
5. [XKDD 22] Improving the quality of rule-based GNN explanations [paper]
6. [Arxiv 22] Differentially Private Graph Neural Networks for Whole-Graph Classification [paper]
7. [Arxiv 22] Explaining Link Predictions in Knowledge Graph Embedding Models with Influential Examples [paper]
8. [AI 22] Are Graph Neural Network Explainers Robust to Graph Noises? [paper]
9. [TAI 22] Prototype-based Interpretable Graph Neural Networks [paper]
10. [CIKM 22] GRETEL: Graph Counterfactual Explanation Evaluation Framework[paper]
11. [LOG 22] Towards Training GNNs using Explanation Directed Message Passing [paper]
12. [AAAI23] On the Limit of Explaining Black-box Temporal Graph Neural Networks [paper]
13. [LOG 22] Towards Training GNNs using Explanation Directed Message Passing [paper]
14. [BRACIS 22] ConveXplainer for Graph Neural Networks [paper]
15. [Arxiv 22] Exploring Explainability Methods for Graph Neural Networks [paper]
16. [Arxiv 22] PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks [paper]
17. [Arxiv 22] Interpretable Geometric Deep Learning via Learnable Randomness Injection [paper]
18. [Arxiv 22] A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation [paper]
19. [Arxiv 22] GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations [paper]
20. [NeurIPS 22] Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure [paper]
21. [Arxiv 22] Global Counterfactual Explainer for Graph Neural Networks [paper]
22. [Arxiv 22] Toward Multiple Specialty Learners for Explaining GNNs via Online Knowledge Distillation [paper]
23. [NeurIPS 22] CLEAR: Generative Counterfactual Explanations on Graphs[paper]
24. [CIKM 22] A Model-Centric Explainer for Graph Neural Network based Node Classification [paper]
25. [GLB 22] An Explainable AI Library for Benchmarking Graph Explainers [paper]
26. [Openreview 23] MEGAN: Multi Explanation Graph Attention Network [paper]
27. [Openreview 23] Explaining Temporal Graph Models through an Explorer-Navigator Framework [paper]
28. [Openreview 23] TGP: Explainable Temporal Graph Neural Networks for Personalized Recommendation [paper]
29. [Openreview 23] Rethinking the Explanation of Graph Neural Network via Non-parametric Subgraph Matching [paper]
30. [Openreview 23] DAG Matters! GFlowNets Enhanced Explainer for Graph Neural Networks [paper]
31. [Openreview 23] On Regularization for Explaining Graph Neural Networks: An Information Theory Perspective [paper]
32. [Openreview 23] A Differential Geometric View and Explainability of GNN on Evolving Graphs [paper]
33. [LOG 22] Global Explainability of GNNs via Logic Combination of Learned Concepts [paper]
34. [MICCAI] Sparse Interpretation of Graph Convolutional Networks for Multi-modal Diagnosis of Alzheimer’s Disease [paper]
35. [Arxiv 22] Learning to Explain Graph Neural Networks [paper]
36. [Arxiv 22] Towards Prototype-Based Self-Explainable Graph Neural Network [paper]
37. [Arxiv 22] PGX: A Multi-level GNN Explanation Framework Based on Separate Knowledge Distillation Processes [paper]
38. [Bioinformatics] GNN-SubNet: disease subnetwork detection with explainable Graph Neural Networks [paper]
39. [Arxiv 22] GGNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks [paper]
40. [Arxiv 22] Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysis [paper]
41. [Arxiv 22] Explainability in subgraphs-enhanced Graph Neural Networks [paper]
42. [Arxiv 22] Defending Against Backdoor Attack on Graph Nerual Network by Explainability [paper]
43. [Arxiv 22] XG-BoT: An Explainable Deep Graph Neural Network for Botnet Detection and Forensics [paper]
44. [Arxiv 22] An Explainer for Temporal Graph Neural Networks [paper]
45. [Arxiv 22] Explaining Dynamic Graph Neural Networks via Relevance Back-propagation [paper]
46. [Infocom 22] Interpretability Evaluation of Botnet Detection Model based on Graph Neural Network [paper]
47. [Arxiv 22] GRETEL: A unified framework for Graph Counterfactual Explanation Evaluation [paper]
48. [TNNLS22] A Meta-Learning Approach for Training Explainable Graph Neural Networks [paper]
49. [Arxiv 22] EiX-GNN : Concept-level eigencentrality explainer for graph neural networks [paper]
50. [IJCAI 22] What Does My GNN Really Capture? On Exploring Internal GNN Representations [paper]
51. [Arxiv 22] MotifExplainer: a Motif-based Graph Neural Network Explainer [paper]
52. [Arxiv 22] Faithful Explanations for Deep Graph Models [paper]
53. [Arxiv 22] Towards Explanation for Unsupervised Graph-Level Representation Learning [paper]
54. [Arxiv 22] BAGEL: A Benchmark for Assessing Graph Neural Network Explanations [paper]
55. [KDD 22] On Structural Explanation of Bias in Graph Neural Networks [paper]
56. [TNNLS 22] Explaining Deep Graph Networks via Input Perturbation [paper]
57. [MICCAI 22] Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis [paper]
58. [IEEE 22] Explaining Graph Neural Networks With Topology-Aware Node Selection: Application in Air Quality Inference [paper]
59. [EuroS&P 22] Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysis [paper]
60. [LOG 22]GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networks [paper]
61. [AISTATS 22] CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks [paper]
62. [AAAI 2022] Prototype-Based Explanations for Graph Neural Networks [paper]
63. [ISBI 22] Interpretable Graph Convolutional Network Of Multi-Modality Brain Imaging For Alzheimer’s Disease Diagnosis [paper]
64. [Medical Imaging 2022] Phenotype guided interpretable graph convolutional network analysis of fMRI data reveals changing brain connectivity during adolescence [paper]
65. [NeuroComputing 22] Perturb more, trap more: Understanding behaviors of graph neural networks [paper]
66. [Arxiv 22] BrainIB: Interpretable Brain Network-based Psychiatric Diagnosis with Graph Information Bottleneck [paper]
67. [DSN 22] CFGExplainer: Explaining Graph Neural Network-Based Malware Classification from Control Flow Graphs [paper]
68. [DASFAA 22] On Global Explainability of Graph Neural Networks [paper]
69. [AAAI 22] KerGNNs: Interpretable Graph Neural Networks with Graph Kernels[paper]
70. [TPAMI 22] Reinforced Causal Explainer for Graph Neural Networks [paper]
71. [Arxiv 22] A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability [paper]
72. [CVPR 22] OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks [paper]
73. [CVPR 22] Improving Subgraph Recognition with Variational Graph Information Bottleneck [paper]
74. [DMKD 22] On GNN explanability with activation patterns [paper]
75. [Arxiv 22] Explainability in Graph Neural Networks: An Experimental Survey [paper]
76. [Arxiv 22] Explainability and Graph Learning from Social Interactions [paper]
77. [AISTATS 22] Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods [paper]
78. [MLOG-WSDM22] Providing Node-level Local Explanation for node2vec through Reinforcement Learning [paper]
79. [The Webconf 22] Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning [paper]
80. [Arxiv 22] GRAPHSHAP: Motif-based Explanations for Black-box Graph Classifiers [paper]
81. [KBS 22] EGNN: Constructing explainable graph neural networks via knowledge distillation [paper]
82. [AAAI22] ProtGNN: Towards Self-Explaining Graph Neural Networks [paper]
83. [ICML 22] Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanism [paper]
84. [Arxiv 22] Explaining Graph-level Predictions with Communication Structure-Aware Cooperative Games [paper]
85. [OpenReview 21] Deconfounding to Explanation Evaluation in Graph Neural Networks [paper]
86. [ICLR 22] Discovering Invariant Rationales for Graph Neural Networks [paper]
87. [BioRxiv 22] GNN-SubNet: disease subnetwork detection with explainable Graph Neural Networks [paper]
88. [Arxiv 22] Cognitive Explainers of Graph Neural Networks Based on Medical Concepts [paper]
89. [Arxiv 22] MotifExplainer: a Motif-based Graph Neural Network Explainer [paper]

Year 2021

1. [Arxiv 21] Towards the Explanation of Graph Neural Networks in Digital Pathology with Information Flows [paper]
2. [IJCKG2021] Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rules [paper]
3. [Arxiv 21] Combining Sub-Symbolic and Symbolic Methods for Explainability [paper]
4. [PAKDD 21] SCARLET: Explainable Attention based Graph Neural Network for Fake News spreader prediction [paper]
5. [J. Chem. Inf. Model] Coloring Molecules with Explainable Artificial Intelligence for Preclinical Relevance Assessment [paper]
6. [BioRxiv 21] APRILE: Exploring the Molecular Mechanisms of Drug Side Effects with Explainable Graph Neural Networks [paper]
7. [ISM 21] Edge-Level Explanations for Graph Neural Networks by Extending Explainability Methods for Convolutional Neural Networks [paper]
8. [TPAMI 21] Higher-Order Explanations of Graph Neural Networks via Relevant Walks [paper]
9. [OpenReview 21] FlowX: Towards Explainable Graph Neural Networks via Message Flows [paper]
10. [NeurIPS 22] Task-Agnostic Graph Neural Explanations [paper]
11. [OpenReview 21] DEGREE: Decomposition Based Explanation for Graph Neural Networks [paper]
12. [OpenReview 21] Explainable GNN-Based Models over Knowledge Graphs [paper]
13. [NeurIPS 2021] Reinforcement Learning Enhanced Explainer for Graph Neural Networks [paper]
14. [NeurIPS 2021] Towards Multi-Grained Explainability for Graph Neural Networks [paper]
15. [NeurIPS 2021] Robust Counterfactual Explanations on Graph Neural Networks [paper]
16. [CVPR 2021] Quantifying Explainers of Graph Neural Networks in Computational Pathology.[paper]
17. [NAACL 2021] Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph Network. [paper]
18. [Arxiv 21] A Meta-Learning Approach for Training Explainable Graph Neural Network [paper]
19. [Arxiv 21] Jointly Attacking Graph Neural Network and its Explanations [paper]
20. [Arxiv 21] SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods [paper]
21. [Arxiv 21] Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks [paper]
22. [Arxiv 21] Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation [paper]
23. [Arxiv 21] Learnt Sparsification for Interpretable Graph Neural Networks [paper]
24. [Arxiv 21] Efficient and Interpretable Robot Manipulation with Graph Neural Networks [paper]
25. [Arxiv 21] IA-GCN: Interpretable Attention based Graph Convolutional Network for Disease prediction [paper]
26. [ICML 2021] On Explainability of Graph Neural Networks via Subgraph Explorations[paper]
27. [ICML 2021] Generative Causal Explanations for Graph Neural Networks[paper]
28. [ICML 2021] Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity[paper]
29. [ICML 2021] Automated Graph Representation Learning with Hyperparameter Importance Explanation[paper]
30. [ICML workshop 21] GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks [paper]
31. [ICML workshop 21] BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis [paper]
32. [ICML workshop 21] Reliable Graph Neural Network Explanations Through Adversarial Training [paper]
33. [ICML workshop 21] Reimagining GNN Explanations with ideas from Tabular Data [paper]
34. [ICML workshop 21] Towards Automated Evaluation of Explanations in Graph Neural Networks [paper]
35. [ICML workshop 21] Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction [paper]
36. [ICML workshop 21] SALKG: Learning From Knowledge Graph Explanations for Commonsense Reasoning [paper]
37. [ICLR 2021] Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking[paper]
38. [ICLR 2021] Graph Information Bottleneck for Subgraph Recognition [paper]
39. [KDD 2021] When Comparing to Ground Truth is Wrong: On Evaluating GNN Explanation Methods[paper]
40. [KDD 2021] Counterfactual Graphs for Explainable Classification of Brain Networks [paper]
41. [AAAI 2021] Motif-Driven Contrastive Learning of Graph Representations [paper]
42. [WWW 2021] Interpreting and Unifying Graph Neural Networks with An Optimization Framework [paper]
43. [ICDM 2021] GNES: Learning to Explain Graph Neural Networks [paper]
44. [ICDM 2021] GCN-SE: Attention as Explainability for Node Classification in Dynamic Graphs [paper]
45. [ICDM 2021] GNES: Learning to Explain Graph Neural Networks [paper]
46. [ICDM 2021] Multi-objective Explanations of GNN Predictions [paper]
47. [CIKM 2021] Towards Self-Explainable Graph Neural Network [paper]
48. [ECML PKDD 2021] GraphSVX: Shapley Value Explanations for Graph Neural Networks [paper]
49. [WiseML 2021] Explainability-based Backdoor Attacks Against Graph Neural Networks [paper]
50. [IJCNN 21] MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks [paper]
51. [ICCSA 2021] Understanding Drug Abuse Social Network Using Weighted Graph Neural Networks Explainer [paper]
52. [NeSy 21] A New Concept for Explaining Graph Neural Networks [paper]
53. [Information Fusion 21] Towards multi-modal causability with Graph Neural Networks enabling information fusion for explainable AI [paper]
54. [Patterns 21] hcga: Highly Comparative Graph Analysis for network phenotyping [paper]

Year 2020

1. [NeurIPS 2020] Parameterized Explainer for Graph Neural Network.[paper]
2. [NeurIPS 2020] PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks [paper]
3. [KDD 2020] XGNN: Towards Model-Level Explanations of Graph Neural Networks [paper]
4. [ACL 2020]GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media. paper
5. [ICML workstop 2020] Contrastive Graph Neural Network Explanation [paper]
6. [ICML workstop 2020] Towards Explainable Graph Representations in Digital Pathology [paper]
7. [NeurIPS workshop 2020] Explaining Deep Graph Networks with Molecular Counterfactuals [paper]
8. [DataMod@CIKM 2020] Exploring Graph-Based Neural Networks for Automatic Brain Tumor Segmentation" [paper]
9. [Arxiv 2020] Graph Neural Networks Including Sparse Interpretability [paper]
10. [OpenReview 20] A Framework For Differentiable Discovery Of Graph Algorithms [paper]
11. [OpenReview 20] Causal Screening to Interpret Graph Neural Networks [paper]
12. [Arxiv 20] xFraud: Explainable Fraud Transaction Detection on Heterogeneous Graphs [paper]
13. [Arxiv 20] Explaining decisions of Graph Convolutional Neural Networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer [paper]
14. [Arxiv 20] Understanding Graph Neural Networks from Graph Signal Denoising Perspectives [paper]
15. [Arxiv 20] Understanding the Message Passing in Graph Neural Networks via Power Iteration [paper]
16. [Arxiv 20] xERTE: Explainable Reasoning on Temporal Knowledge Graphs for Forecasting Future Links [paper]
17. [IJCNN 20] GCN-LRP explanation: exploring latent attention of graph convolutional networks] [paper]
18. [Arxiv 20] Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification] [paper]