# Learning Actionable Counterfactual Explanations in Large State Spaces

arXiv: https://arxiv.org/abs/2404.17034 · HTML: https://mlsanity.com/paper/2404.17034/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 49 references that are in the map.
- First posted on arXiv 25 Apr 2024.

## Builds on (most cited first, 25 of 25)

- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [CVXPY: A Python-Embedded Modeling Language for Convex Optimization](https://mlsanity.com/paper/1603.00943/) (2016)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Actionable Recourse in Linear Classification](https://mlsanity.com/paper/1809.06514/) (2018)
- [Algorithmic Recourse: from Counterfactual Explanations to Interventions](https://mlsanity.com/paper/2002.06278/) (2020)
- [A Rewriting System for Convex Optimization Problems](https://mlsanity.com/paper/1709.04494/) (2017)
- [Multi-Objective Counterfactual Explanations](https://mlsanity.com/paper/2004.11165/) (2020)
- [Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems](https://mlsanity.com/paper/1907.09615/) (2019)
- [The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons](https://mlsanity.com/paper/1912.04930/) (2019)
- [A PAC Approach to Application-Specific Algorithm Selection](https://mlsanity.com/paper/1511.07147/) (2015)
- [Equalizing Recourse across Groups](https://mlsanity.com/paper/1909.03166/) (2019)
- [Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis](https://mlsanity.com/paper/2106.09992/) (2021)
- [Robust Counterfactual Explanations in Machine Learning: A Survey](https://mlsanity.com/paper/2402.01928/) (2024)
- [GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanations](https://mlsanity.com/paper/2305.17021/) (2023)
- [Amortized Generation of Sequential Algorithmic Recourses for Black-box Models](https://mlsanity.com/paper/2106.03962/) (2021)
- [Synthesizing Action Sequences for Modifying Model Decisions](https://mlsanity.com/paper/1910.00057/) (2019)
- [Data-Driven Clustering via Parameterized Lloyd's Families](https://mlsanity.com/paper/1809.06987/) (2018)
- [Consequence-aware Sequential Counterfactual Generation](https://mlsanity.com/paper/2104.05592/) (2021)
- [CARE: Coherent Actionable Recourse based on Sound Counterfactual Explanations](https://mlsanity.com/paper/2108.08197/) (2021)
- [A unified logical framework for explanations in classifier systems](https://mlsanity.com/paper/2105.14452/) (2021)
- [An ASP-Based Approach to Counterfactual Explanations for Classification](https://mlsanity.com/paper/2004.13237/) (2020)
- [Generating collective counterfactual explanations in score-based classification via mathematical optimization](https://mlsanity.com/paper/2310.12822/) (2023)
- [Extracting Incentives from Black-Box Decisions](https://mlsanity.com/paper/1910.05664/) (2019)
- [Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis](https://mlsanity.com/paper/2201.07135/) (2022)
- [Comparison of 14 different families of classification algorithms on 115 binary datasets](https://mlsanity.com/paper/1606.00930/) (2016)

## Built on by (most cited first, 1 of 1)

- [Revealing Positive and Negative Role Models to Help People Make Good Decisions](https://mlsanity.com/paper/2603.02495/) (2026)

## Abstract (arXiv)

Recourse generators provide actionable insights, often through feature-based counterfactual explanations (CFEs), to help negatively classified individuals understand how to adjust their input features to achieve a positive classification. These feature-based CFEs, which we refer to as low-level CFEs, are overly specific (e.g., coding experience: (4 → 5+) years) and often recommended in a feature space that doesn't straightforwardly align with real-world actions. To bridge this gap, we introduce three novel recourse types grounded in real-world actions: high-level continuous (hl-continuous), high-level discrete (hl-discrete), and high-level ID (hl-id) CFEs. We formulate single-agent CFE generation methods, where we model the hl-discrete CFE as a solution to a weighted set cover problem and the hl-continuous CFE as a solution to an integer linear program. Since these methods require costly optimization per agent, we propose data-driven CFE generation approaches that, given instances of agents and their optimal CFEs, learn a CFE generator that quickly provides optimal CFEs for new agents. This approach, also viewed as one of learning an optimal policy in a family of large but deterministic MDPs, considers several problem formulations, including formulations in which the actions and their effects are unknown, and therefore addresses informational and computational challenges. We conduct extensive empirical evaluations using healthcare datasets (BRFSS, Foods, and NHANES) and fully-synthetic data. For negatively classified agents identified by linear or threshold-based classifiers, we compare the high-level CFE to low-level CFEs and assess the effectiveness of our network-based, data-driven approaches. Results show that the data-driven CFE generators are accurate, and resource-efficient, and high-level CFEs offer key advantages over low-level CFEs.