mlsanityData to 7 Oct 2026

A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges

arXiv 2210.12089 ↗First posted 21 Oct 2022cs.LG cs.AIcited by 30

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) perform well in community detection and molecule classification. Counterfactual Explanations (CE) provide counter-examples to overcome the transparency limitations of black-box models. Due to the growing attention in graph learning, we focus on the concepts of CE for GNNs. We analysed the SoA to provide a taxonomy, a uniform notation, and the benchmarking datasets and evaluation metrics. We discuss fourteen methods, their evaluation protocols, twenty-two datasets, and nineteen metrics. We integrated the majority of methods into the GRETEL library to conduct an empirical evaluation to understand their strengths and pitfalls. We highlight open challenges and future work.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 93 of its 199 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

93 of 199 references.

References · 93

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2017Graph Attention Networkscited by 8,854
  7. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  8. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  10. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  11. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  12. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
38 more
  1. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  2. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  3. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  4. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  5. 2016Understanding intermediate layers using linear classifier probescited by 1,279
  6. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  7. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  8. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  9. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  10. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,037
  11. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  12. 2019Attention is not Explanationcited by 916
  13. 2018Link Prediction Based on Graph Neural Networkscited by 829
  14. 2015Gated Graph Sequence Neural Networkscited by 792
  15. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  16. 2017Deep Reinforcement Learning that Matterscited by 727
  17. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  18. 2019DropEdge: Towards Deep Graph Convolutional Networks on Node Classificationcited by 679
  19. 2019Neural Graph Collaborative Filteringcited by 660
  20. 2015LINE: Large-scale Information Network Embeddingcited by 582
  21. 2020Directional Message Passing for Molecular Graphscited by 556
  22. 2019Multi-scale Attributed Node Embeddingcited by 543
  23. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  24. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  25. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  26. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  27. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  28. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  29. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  30. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  31. 2018Explainable Prediction of Medical Codes from Clinical Textcited by 231
  32. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  33. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  34. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  35. 2018Optimization of Molecules via Deep Reinforcement Learningcited by 199
  36. 2021Identity-aware Graph Neural Networkscited by 197
  37. 2020Fairness in Machine Learningcited by 194
  38. 2021GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networkscited by 147

50 most cited of 93 All 93 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 9; 2025: 7; 2026: 6.

30 papers.

Sort:

By area:

  1. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  2. 2024How Interpretable Are Interpretable Graph Neural Networks?cited by 13
  3. 2023GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarkingcited by 11
  4. 2024A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classificationcited by 9
  5. 2023Generative Explanations for Graph Neural Network: Methods and Evaluationscited by 4
  6. 2023When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlookcited by 4
  7. 2024On Explaining Unfairness: An Overviewcited by 3
  8. 2024Counterfactual Explanations for Deep Learning-Based Traffic Forecastingcited by 3
  9. 2024Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inferencecited by 3
  10. 2023Unstructured and structured data: Can we have the best of both worlds with large language models?cited by 2
  11. 2023Counterfactual Explanations for Graph Classification Through the Lenses of Densitycited by 2
  12. 2024CoDy: Counterfactual Explainers for Dynamic Graphscited by 2
18 more
  1. 2024Towards Fair Graph Neural Networks via Graph Counterfactual without Sensitive Attributescited by 2
  2. 2025Graph Inverse Style Transfer for Counterfactual Explainabilitycited by 2
  3. 2026ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networkscited by 2
  4. 2023Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapescited by 1
  5. 2024Introducing Diminutive Causal Structure into Graph Representation Learningcited by 1
  6. 2025Improving Counterfactual Truthfulness for Molecular Property Prediction through Uncertainty Quantificationcited by 1
  7. 2025Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMscited by 1
  8. 2026Faithful, Sufficient and Understandable: Rethinking Graph Counterfactual Explanations via Discrete Diffusion Inversioncited by 1
  9. 2023Introducing Expertise Logic into Graph Representation Learning from A Causal Perspectivecited by 0
  10. 2024Global Graph Counterfactual Explanation: A Subgraph Mapping Approachcited by 0
  11. 2025Analysis of Customer Journeys Using Prototype Detection and Counterfactual Explanations for Sequential Datacited by 0
  12. 2025UGCE: User-Guided Incremental Counterfactual Explorationcited by 0
  13. 2025Learning Marked Temporal Point Process Explanations based on Counterfactual and Factual Reasoningcited by 0
  14. 2025Counterfactual Explanation for Multivariate Time Series Forecasting with Exogenous Variablescited by 0
  15. 2026GradCFA: A Hybrid Gradient-Based Counterfactual and Feature Attribution Explanation Algorithm for Local Interpretation of Neural Networkscited by 0
  16. 2026Advancing Edge Classification through High-Dimensional Causal Modeling of Node-Edge Interplaycited by 0
  17. 2026Counterfactuals for Feature-Weighted Clusteringcited by 0
  18. 2026From Explanations to Interventions: Execution-Guided Counterfactual Synthesis in Temporal Graphscited by 0