mlsanityData to 7 Oct 2026

Counterfactual Graphs for Explainable Classification of Brain Networks

arXiv 2106.08640 ↗First posted 16 Jun 2021cs.SI cs.LGcited by 33

Not on the map. Why?

Abstract (arXiv)

Training graph classifiers able to distinguish between healthy brains and dysfunctional ones, can help identifying substructures associated to specific cognitive phenotypes. However, the mere predictive power of the graph classifier is of limited interest to the neuroscientists, which have plenty of tools for the diagnosis of specific mental disorders. What matters is the interpretation of the model, as it can provide novel insights and new hypotheses. In this paper we propose counterfactual graphs as a way to produce local post-hoc explanations of any black-box graph classifier. Given a graph and a black-box, a counterfactual is a graph which, while having high structural similarity with the original graph, is classified by the black-box in a different class. We propose and empirically compare several strategies for counterfactual graph search. Our experiments against a white-box classifier with known optimal counterfactual, show that our methods, although heuristic, can produce counterfactuals very close to the optimal one. Finally, we show how to use counterfactual graphs to build global explanations correctly capturing the behaviour of different black-box classifiers and providing interesting insights for the neuroscientists.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). Builds on 14 of its 50 references that are in the map. First posted on arXiv 16 Jun 2021.

Builds on

14 of 50 references.

References · 14

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  4. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  6. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  7. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  8. 2017graph2vec: Learning Distributed Representations of Graphscited by 228
  9. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  10. 2020Explainable deep learning models in medical image analysiscited by 111
  11. 2019DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classificationcited by 59
  12. 2020RelEx: A Model-Agnostic Relational Model Explainercited by 53
2 more
  1. 2020Explainable Classification of Brain Networks via Contrast Subgraphscited by 26
  2. 2020Explaining Deep Graph Networks with Molecular Counterfactualscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 10; 2024: 7; 2025: 5; 2026: 3.

33 papers.

Sort:

  1. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  2. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  3. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  4. 2022Global Counterfactual Explainer for Graph Neural Networkscited by 30
  5. 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
  6. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  7. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  8. 2024Graph Neural Networks for Vulnerability Detection: A Counterfactual Explanationcited by 12
  9. 2023GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarkingcited by 11
  10. 2024Comprehensible Artificial Intelligence on Knowledge Graphs: A surveycited by 8
  11. 2022GRAPHSHAP: Explaining Identity-Aware Graph Classifiers Through the Language of Motifscited by 6
  12. 2022GRETEL: A unified framework for Graph Counterfactual Explanation Evaluationcited by 6
21 more
  1. 2022Anomaly Detection in Multiplex Dynamic Networks: from Blockchain Security to Brain Disease Predictioncited by 6
  2. 2025From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Contextcited by 6
  3. 2022CS-MLGCN : Multiplex Graph Convolutional Networks for Community Search in Multiplex Networkscited by 5
  4. 2023CS-TGN: Community Search via Temporal Graph Neural Networkscited by 4
  5. 2023Bridging Trustworthiness and Open-World Learning: An Exploratory Neural Approach for Enhancing Interpretability, Generalization, and Robustnesscited by 4
  6. 2023When Graph Neural Network Meets Causality: Opportunities, Methodologies and An Outlookcited by 4
  7. 2024Explaining Graph Neural Networks with Large Language Models: A Counterfactual Perspective for Molecular Property Predictioncited by 3
  8. 2024SurfGNN: A robust surface-based prediction model with interpretability for coactivation maps of spatial and cortical featurescited by 3
  9. 2023Counterfactual Explanations for Graph Classification Through the Lenses of Densitycited by 2
  10. 2024Towards Non-Adversarial Algorithmic Recoursecited by 2
  11. 2025Graph Inverse Style Transfer for Counterfactual Explainabilitycited by 2
  12. 2026ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networkscited by 2
  13. 2023Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapescited by 1
  14. 2024Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learningcited by 1
  15. 2025COMRECGC: Global Graph Counterfactual Explainer through Common Recoursecited by 1
  16. 2025Finding Counterfactual Evidences for Node Classificationcited by 1
  17. 2023Empowering Counterfactual Reasoning over Graph Neural Networks through Inductivitycited by 0
  18. 2024Global Graph Counterfactual Explanation: A Subgraph Mapping Approachcited by 0
  19. 2025Learning Marked Temporal Point Process Explanations based on Counterfactual and Factual Reasoningcited by 0
  20. 2026CFRecs: Counterfactual Recommendations on Real Estate User Listing Interaction Graphscited by 0
  21. 2026NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruptioncited by 0