A causal process model for algorithmic recourse introduces post-recourse stability conditions and copula-based methods to infer intervention effects from observational or paired data, with a distribution-free fallback when the model is rejected.
Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
abstract
Machine learning based decision making systems are increasingly affecting humans. An individual can suffer an undesirable outcome under such decision making systems (e.g. denied credit) irrespective of whether the decision is fair or accurate. Individual recourse pertains to the problem of providing an actionable set of changes a person can undertake in order to improve their outcome. We propose a recourse algorithm that models the underlying data distribution or manifold. We then provide a mechanism to generate the smallest set of changes that will improve an individual's outcome. This mechanism can be easily used to provide recourse for any differentiable machine learning based decision making system. Further, the resulting algorithm is shown to be applicable to both supervised classification and causal decision making systems. Our work attempts to fill gaps in existing fairness literature that have primarily focused on discovering and/or algorithmically enforcing fairness constraints on decision making systems. This work also provides an alternative approach to generating counterfactual explanations.
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Proposes diffeomorphic optimization for manifold-constrained problems in generative models via flow maps, with Lie-group extensions for protein design showing metric improvements.
Introduces learning-augmented robust algorithmic recourse that trades off consistency with accurate future-model predictions against robustness to inaccurate predictions via a novel algorithm.
TabChange produces more proximal and valid counterfactuals on tabular data by relationship-based flipping or adversarial latent-space attribute removal compared to baselines on seven datasets.
Interpretability research should be judged by actionability—the degree to which its insights support concrete decisions and interventions—rather than explanatory power alone.
Formalizing personalization as individual actionability in causal recourse shows hard constraints degrade validity and plausibility while revealing socio-demographic disparities in costs.
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.
TRUST searches for minimal input changes that achieve a user-defined confidence target in PTM models, claiming perfect robustness and low cost on benchmarks versus standard boundary-crossing methods.
citing papers explorer
-
Causal Algorithmic Recourse: Foundations and Methods
A causal process model for algorithmic recourse introduces post-recourse stability conditions and copula-based methods to infer intervention effects from observational or paired data, with a distribution-free fallback when the model is rejected.
-
Diffeomorphic Optimization
Proposes diffeomorphic optimization for manifold-constrained problems in generative models via flow maps, with Lie-group extensions for protein design showing metric improvements.
-
Learning-Augmented Robust Algorithmic Recourse
Introduces learning-augmented robust algorithmic recourse that trades off consistency with accurate future-model predictions against robustness to inaccurate predictions via a novel algorithm.
-
TabChange: Precise Attribute Changes in Tabular Data
TabChange produces more proximal and valid counterfactuals on tabular data by relationship-based flipping or adversarial latent-space attribute removal compared to baselines on seven datasets.
-
Interpretability Can Be Actionable
Interpretability research should be judged by actionability—the degree to which its insights support concrete decisions and interventions—rather than explanatory power alone.
-
From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recourse
Formalizing personalization as individual actionability in causal recourse shows hard constraints degrade validity and plausibility while revealing socio-demographic disparities in costs.
-
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.
-
Target-confidence Recourse Using tSeTlin machines: TRUST
TRUST searches for minimal input changes that achieve a user-defined confidence target in PTM models, claiming perfect robustness and low cost on benchmarks versus standard boundary-crossing methods.
- When Bits Break Recourse: Counterfactual-Faithful Quantization