mlsanityData to 14 Oct 2026

CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks

arXiv 2102.03322 ↗First posted 5 Feb 2021cs.LG cs.AIcited by 119

Not on the map. Why?

Abstract (arXiv)

Given the increasing promise of graph neural networks (GNNs) in real-world applications, several methods have been developed for explaining their predictions. Existing methods for interpreting predictions from GNNs have primarily focused on generating subgraphs that are especially relevant for a particular prediction. However, such methods are not counterfactual (CF) in nature: given a prediction, we want to understand how the prediction can be changed in order to achieve an alternative outcome. In this work, we propose a method for generating CF explanations for GNNs: the minimal perturbation to the input (graph) data such that the prediction changes. Using only edge deletions, we find that our method, CF-GNNExplainer, can generate CF explanations for the majority of instances across three widely used datasets for GNN explanations, while removing less than 3 edges on average, with at least 94% accuracy. This indicates that CF-GNNExplainer primarily removes edges that are crucial for the original predictions, resulting in minimal CF explanations.

Key facts. Cited by 119 papers in the map (data through 14 Oct 2026). Builds on 36 of its 61 references that are in the map. First posted on arXiv 5 Feb 2021.

Builds on

36 of 61 references.

References · 36

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  5. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  6. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  7. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
  8. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  9. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  10. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  11. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  12. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
24 more
  1. 2018Actionable Recourse in Linear Classificationcited by 328
  2. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  3. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  4. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 211
  5. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  6. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  7. 2018Adversarial Attack and Defense on Graph Data: A Surveycited by 167
  8. 2018Local Rule-Based Explanations of Black Box Decision Systemscited by 166
  9. 2019Explainability Techniques for Graph Convolutional Networkscited by 161
  10. 2020Machine Learning on Graphs: A Model and Comprehensive Taxonomycited by 156
  11. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  12. 2020A survey of algorithmic recourse: definitions, formulations, solutions, and prospectscited by 118
  13. 2019The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasonscited by 115
  14. 2017Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweakingcited by 76
  15. 2016Training Sparse Neural Networkscited by 73
  16. 2017Inverse Classification for Comparison-based Interpretability in Machine Learningcited by 50
  17. 2020The Intriguing Relation Between Counterfactual Explanations and Adversarial Examplescited by 44
  18. 2019FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensemblescited by 43
  19. 2019Why Does My Model Fail? Contrastive Local Explanations for Retail Forecastingcited by 31
  20. 2020BRPO: Batch Residual Policy Optimizationcited by 25
  21. 2019Drug-Drug Adverse Effect Prediction with Graph Co-Attentioncited by 20
  22. 2020Contrastive Graph Neural Network Explanationcited by 20
  23. 2020Preserving Integrity in Online Social Networkscited by 14
  24. 2019ExplaiNE: An Approach for Explaining Network Embedding-based Link Predictionscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 27; 2023: 25; 2024: 20; 2025: 18; 2026: 18.

119 papers.

Sort:

By area:

  1. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  2. 2022Data Augmentation for Deep Graph Learning: A Surveycited by 133
  3. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 89
  4. 2022Evaluating Explainability for Graph Neural Networkscited by 87
  5. 2022Debiasing Graph Neural Networks via Learning Disentangled Causal Substructurecited by 83
  6. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
  7. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  8. 2024Position: Topological Deep Learning is the New Frontier for Relational Learningcited by 66
  9. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 58
  10. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  11. 2023Does Invariant Graph Learning via Environment Augmentation Learn Invariance?cited by 42
  12. 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
38 more
  1. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 35
  2. 2022Global Counterfactual Explainer for Graph Neural Networkscited by 30
  3. 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
  4. 2023A Survey on Explainability of Graph Neural Networkscited by 29
  5. 2021Counterfactual Explanations for Neural Recommenderscited by 27
  6. 2022Fairness in Recommendation: Foundations, Methods and Applicationscited by 27
  7. 2021ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Modelscited by 25
  8. 2023PaGE-Link: Path-based Graph Neural Network Explanation for Heterogeneous Link Predictioncited by 25
  9. 2022GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendationscited by 22
  10. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  11. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  12. 2022Encoding Concepts in Graph Neural Networkscited by 18
  13. 2023Distill n' Explain: explaining graph neural networks using simple surrogatescited by 18
  14. 2023DEGREE: Decomposition Based Explanation For Graph Neural Networkscited by 18
  15. 2021A Meta-Learning Approach for Training Explainable Graph Neural Networkscited by 15
  16. 2022Exploring Faithful Rationale for Multi-hop Fact Verification via Salience-Aware Graph Learningcited by 15
  17. 2023Illuminati: Towards Explaining Graph Neural Networks for Cybersecurity Analysiscited by 14
  18. 2022Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challengescited by 12
  19. 2022On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approachcited by 11
  20. 2023GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarkingcited by 11
  21. 2024GraphXAIN: Narratives to Explain Graph Neural Networkscited by 11
  22. 2022Towards Explainable Motion Prediction using Heterogeneous Graph Representationscited by 10
  23. 2023Probing Graph Representationscited by 10
  24. 2024GOAt: Explaining Graph Neural Networks via Graph Output Attributioncited by 10
  25. 2024LLM-Powered Explanations: Unraveling Recommendations Through Subgraph Reasoningcited by 10
  26. 2023Deep Backtracking Counterfactuals for Causally Compliant Explanationscited by 9
  27. 2023D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusioncited by 9
  28. 2022Cardinality-Minimal Explanations for Monotonic Neural Networkscited by 8
  29. 2023Exploring Causal Learning through Graph Neural Networks: An In-depth Reviewcited by 8
  30. 2024LOGIN: A Large Language Model Consulted Graph Neural Network Training Frameworkcited by 8
  31. 2021Learning through structure: towards deep neuromorphic knowledge graph embeddingscited by 7
  32. 2022L2XGNN: Learning to Explain Graph Neural Networkscited by 7
  33. 2022Towards Training GNNs using Explanation Directed Message Passingcited by 7
  34. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 7
  35. 2022GRETEL: A unified framework for Graph Counterfactual Explanation Evaluationcited by 6
  36. 2024Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanationcited by 6
  37. 2022Sparse Vicious Attacks on Graph Neural Networkscited by 5
  38. 2022PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networkscited by 5

50 most cited of 119 All 119 (JSON)