mlsanityData to 14 Oct 2026

Graph Inverse Style Transfer for Counterfactual Explainability

arXiv 2505.17542 ↗First posted 23 May 2025cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Counterfactual explainability seeks to uncover model decisions by identifying minimal changes to the input that alter the predicted outcome. This task becomes particularly challenging for graph data due to preserving structural integrity and semantic meaning. Unlike prior approaches that rely on forward perturbation mechanisms, we introduce Graph Inverse Style Transfer (GIST), the first framework to re-imagine graph counterfactual generation as a backtracking process, leveraging spectral style transfer. By aligning the global structure with the original input spectrum and preserving local content faithfulness, GIST produces valid counterfactuals as interpolations between the input style and counterfactual content. Tested on 8 binary and multi-class graph classification benchmarks, GIST achieves a remarkable +7.6% improvement in the validity of produced counterfactuals and significant gains (+45.5%) in faithfully explaining the true class distribution. Additionally, GIST's backtracking mechanism effectively mitigates overshooting the underlying predictor's decision boundary, minimizing the spectral differences between the input and the counterfactuals. These results challenge traditional forward perturbation methods, offering a novel perspective that advances graph explainability.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 33 of its 69 references that are in the map. First posted on arXiv 23 May 2025.

Builds on

33 of 69 references.

References · 33

  1. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  2. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  3. 2015Pointer Networkscited by 895
  4. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  5. 2020Benchmarking Graph Neural Networkscited by 680
  6. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 506
  7. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  8. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  9. 2017Style Transfer from Non-Parallel Text by Cross-Alignmentcited by 248
  10. 2018Optimization of Molecules via Deep Reinforcement Learningcited by 200
  11. 2017Demystifying Neural Style Transfercited by 152
  12. 2017Controlling Linguistic Style Aspects in Neural Language Generationcited by 149
21 more
  1. 2017Style Transfer in Text: Exploration and Evaluationcited by 146
  2. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 119
  3. 2014Propagation Kernelscited by 88
  4. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
  5. 2016Training Sparse Neural Networkscited by 73
  6. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  7. 2017Shakespearizing Modern Language Using Copy-Enriched Sequence-to-Sequence Modelscited by 57
  8. 2023Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detectioncited by 42
  9. 2019Universal Graph Transformer Self-Attention Networkscited by 41
  10. 2021Graph Domain Adaptation: A Generative Viewcited by 35
  11. 2021Counterfactual Graphs for Explainable Classification of Brain Networkscited by 33
  12. 2021MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networkscited by 32
  13. 2022Global Counterfactual Explainer for Graph Neural Networkscited by 30
  14. 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
  15. 2016Preserving Color in Neural Artistic Style Transfercited by 20
  16. 2022CLARE: A Semi-supervised Community Detection Algorithmcited by 13
  17. 2022Are we certain it's anomalous?cited by 13
  18. 2024Semantically Guided Representation Learning For Action Anticipationcited by 10
  19. 2023Robust Stochastic Graph Generator for Counterfactual Explanationscited by 7
  20. 2024Towards Non-Adversarial Algorithmic Recoursecited by 2
  21. 2017Is writing style predictive of scientific fraud?cited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networkscited by 0
  2. 2026A Comparative Study of Counterfactual Explainers for Graph Neural Networks Enabling Multiple Types of Graph Editcited by 0