# RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model

arXiv: https://arxiv.org/abs/2206.00700 · HTML: https://mlsanity.com/paper/2206.00700/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 58 references that are in the map.
- First posted on arXiv 1 Jun 2022.

## Builds on (most cited first, 30 of 43)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Hidden Trigger Backdoor Attacks](https://mlsanity.com/paper/1910.00033/) (2019)
- [Gradient-based Hyperparameter Optimization through Reversible Learning](https://mlsanity.com/paper/1502.03492/) (2015)
- [Actionable Recourse in Linear Classification](https://mlsanity.com/paper/1809.06514/) (2018)
- [Adversarially Robust Generalization Requires More Data](https://mlsanity.com/paper/1804.11285/) (2018)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [Algorithmic Recourse: from Counterfactual Explanations to Interventions](https://mlsanity.com/paper/2002.06278/) (2020)
- [Interpretable Counterfactual Explanations Guided by Prototypes](https://mlsanity.com/paper/1907.02584/) (2019)
- [Truncated Back-propagation for Bilevel Optimization](https://mlsanity.com/paper/1810.10667/) (2018)
- [Learning Model-Agnostic Counterfactual Explanations for Tabular Data](https://mlsanity.com/paper/1910.09398/) (2019)
- [Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers](https://mlsanity.com/paper/1912.03277/) (2019)
- [On the Convergence and Robustness of Adversarial Training](https://mlsanity.com/paper/2112.08304/) (2021)
- [MetaPoison: Practical General-purpose Clean-label Data Poisoning](https://mlsanity.com/paper/2004.00225/) (2020)
- [A survey of algorithmic recourse: definitions, formulations, solutions, and prospects](https://mlsanity.com/paper/2010.04050/) (2020)
- [The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons](https://mlsanity.com/paper/1912.04930/) (2019)
- [Towards Robust and Reliable Algorithmic Recourse](https://mlsanity.com/paper/2102.13620/) (2021)
- [Curriculum Adversarial Training](https://mlsanity.com/paper/1805.04807/) (2018)
- [On Counterfactual Explanations under Predictive Multiplicity](https://mlsanity.com/paper/2006.13132/) (2020)
- [How Important Is a Neuron?](https://mlsanity.com/paper/1805.12233/) (2018)

## Built on by (most cited first, 11 of 11)

- [Robust Counterfactual Explanations in Machine Learning: A Survey](https://mlsanity.com/paper/2402.01928/) (2024)
- [Interval Abstractions for Robust Counterfactual Explanations](https://mlsanity.com/paper/2404.13736/) (2024)
- [Learning-Augmented Robust Algorithmic Recourse](https://mlsanity.com/paper/2410.01580/) (2024)
- [Optimal Robust Recourse with Lp-Bounded Model Change](https://mlsanity.com/paper/2509.21293/) (2025)
- [Understanding Endogenous Data Drift in Adaptive Models with Recourse-Seeking Users](https://mlsanity.com/paper/2503.09658/) (2025)
- [The Role of Causality in Algorithmic Recourse](https://mlsanity.com/paper/2607.28497/) (2026)
- [Watermarking Counterfactual Explanations](https://mlsanity.com/paper/2405.18671/) (2024)
- [DiCE-Extended: A Robust Approach to Counterfactual Explanations in Machine Learning](https://mlsanity.com/paper/2504.19027/) (2025)
- [Tabular Diffusion Counterfactual Explanations](https://mlsanity.com/paper/2509.00876/) (2025)
- [An Explainable Gaussian Process Auto-encoder for Tabular Data](https://mlsanity.com/paper/2509.00884/) (2025)
- [Algorithmic Recourse Under Competition](https://mlsanity.com/paper/2609.39877/) (2026)

## Abstract (arXiv)

Counterfactual (CF) explanations for machine learning (ML) models are preferred by end-users, as they explain the predictions of ML models by providing a recourse (or contrastive) case to individuals who are adversely impacted by predicted outcomes. Existing CF explanation methods generate recourses under the assumption that the underlying target ML model remains stationary over time. However, due to commonly occurring distributional shifts in training data, ML models constantly get updated in practice, which might render previously generated recourses invalid and diminish end-users trust in our algorithmic framework. To address this problem, we propose RoCourseNet, a training framework that jointly optimizes predictions and recourses that are robust to future data shifts. This work contains four key contributions: (1) We formulate the robust recourse generation problem as a tri-level optimization problem which consists of two sub-problems: (i) a bi-level problem that finds the worst-case adversarial shift in the training data, and (ii) an outer minimization problem to generate robust recourses against this worst-case shift. (2) We leverage adversarial training to solve this tri-level optimization problem by: (i) proposing a novel virtual data shift (VDS) algorithm to find worst-case shifted ML models via explicitly considering the worst-case data shift in the training dataset, and (ii) a block-wise coordinate descent procedure to optimize for prediction and corresponding robust recourses. (3) We evaluate RoCourseNet's performance on three real-world datasets, and show that RoCourseNet consistently achieves more than 96% robust validity and outperforms state-of-the-art baselines by at least 10% in generating robust CF explanations. (4) Finally, we generalize the RoCourseNet framework to accommodate any parametric post-hoc methods for improving robust validity.