A latent adjustment method identifies sparse counterfactual factors and computes minimal feasible survey-variable changes to align target respondent distributions with reference groups using entropy-regularized optimal transport and weighted l2,1 sparsity.
Counterfactual explanations and algorithmic recourses for machine learning: A review
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
C-MADF learns a structural causal model to restrict response actions in an MDP and uses dual blue-red RL policies to achieve 1.8% false-positive rate and 0.979 F1 on the CICIoT2023 dataset.
An explainability-aware L0 penalty yields coherent counterfactual edits, and the same geometry defines a Tolerance-Region Confusion Matrix that quantifies class-to-class fragility under interpretable perturbations.
citing papers explorer
-
Discovering Sparse Counterfactual Factors via Latent Adjustment for Survey-based Community Intervention
A latent adjustment method identifies sparse counterfactual factors and computes minimal feasible survey-variable changes to align target respondent distributions with reference groups using entropy-regularized optimal transport and weighted l2,1 sparsity.
-
Explainable Autonomous Cyber Defense using Adversarial Multi-Agent Reinforcement Learning
C-MADF learns a structural causal model to restrict response actions in an MDP and uses dual blue-red RL policies to achieve 1.8% false-positive rate and 0.979 F1 on the CICIoT2023 dataset.
-
Optimized Instance Alteration for Explaining and Assessing Robustness of Classifiers
An explainability-aware L0 penalty yields coherent counterfactual edits, and the same geometry defines a Tolerance-Region Confusion Matrix that quantifies class-to-class fragility under interpretable perturbations.