Explaining and visualizing black-box models through counterfactual paths
Not on the map. Why?
Abstract (arXiv)
Explainable AI (XAI) is an increasingly important area of machine learning research, which aims to make black-box models transparent and interpretable. In this paper, we propose a novel approach to XAI that uses the so-called counterfactual paths generated by conditional permutations of features. The algorithm measures feature importance by identifying sequential permutations of features that most influence changes in model predictions. It is particularly suitable for generating explanations based on counterfactual paths in knowledge graphs incorporating domain knowledge. Counterfactual paths introduce an additional graph dimension to current XAI methods in both explaining and visualizing black-box models. Experiments with synthetic and medical data demonstrate the practical applicability of our approach.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 28 of its 71 references that are in the map. First posted on arXiv 15 Jul 2023.
Builds on
28 of 71 references.
References · 28
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
- 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
- 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 373
- 2019On the (In)fidelity and Sensitivity for Explanationscited by 310
- 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 233
- 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 208
- 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
- 2020Multi-Objective Counterfactual Explanationscited by 157
- 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 91
- 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
- 2020A Tutorial on Learning With Bayesian Networkscited by 57
16 more
- 2021On the Adversarial Robustness of Causal Algorithmic Recoursecited by 56
- 2018Visualizing the Feature Importance for Black Box Modelscited by 55
- 2022Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recoursecited by 40
- 2020Model-agnostic Feature Importance and Effects with Dependent Features -- A Conditional Subgroup Approachcited by 37
- 2019Testing Conditional Independence in Supervised Learning Algorithmscited by 27
- 2023GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanationscited by 27
- 2020Transparency, Auditability and eXplainability of Machine Learning Models in Credit Scoringcited by 26
- 2020The Grammar of Interactive Explanatory Model Analysiscited by 24
- 2021Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Processcited by 24
- 2022SurvSHAP(t): Time-dependent explanations of machine learning survival modelscited by 24
- 2014Bayesian Network Constraint-Based Structure Learning Algorithms: Parallel and Optimised Implementations in the bnlearn R Packagecited by 19
- 2021Diverse, Global and Amortised Counterfactual Explanations for Uncertainty Estimatescited by 19
- 2022Evaluating Feature Attribution Methods in the Image Domaincited by 19
- 2021Grouped Feature Importance and Combined Features Effect Plotcited by 14
- 2022Conditional Feature Importance for Mixed Datacited by 7
- 2021Graph-guided random forest for gene set selectioncited by 2
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.