# Generalized Inverse Classification

arXiv: https://arxiv.org/abs/1610.01675 · HTML: https://mlsanity.com/paper/1610.01675/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Oct 2016.

## Built on by (most cited first, 22 of 22)

- [CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms](https://mlsanity.com/paper/2108.00783/) (2021)
- [Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applications](https://mlsanity.com/paper/2103.04244/) (2021)
- [Consistent Counterfactuals for Deep Models](https://mlsanity.com/paper/2110.03109/) (2021)
- [Amortized Generation of Sequential Algorithmic Recourses for Black-box Models](https://mlsanity.com/paper/2106.03962/) (2021)
- [Consequence-aware Sequential Counterfactual Generation](https://mlsanity.com/paper/2104.05592/) (2021)
- [Achieving Diversity in Counterfactual Explanations: a Review and Discussion](https://mlsanity.com/paper/2305.05840/) (2023)
- [Solving the Class Imbalance Problem Using a Counterfactual Method for Data Augmentation](https://mlsanity.com/paper/2111.03516/) (2021)
- [CeFlow: A Robust and Efficient Counterfactual Explanation Framework for Tabular Data using Normalizing Flows](https://mlsanity.com/paper/2303.14668/) (2023)
- [Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations](https://mlsanity.com/paper/2309.04676/) (2023)
- [Sparse and Faithful Explanations Without Sparse Models](https://mlsanity.com/paper/2402.09702/) (2024)
- [Integrating Prior Knowledge in Post-hoc Explanations](https://mlsanity.com/paper/2204.11634/) (2022)
- [TrustyAI Explainability Toolkit](https://mlsanity.com/paper/2104.12717/) (2021)
- [Causality-based Counterfactual Explanation for Classification Models](https://mlsanity.com/paper/2105.00703/) (2021)
- [RAGUEL: Recourse-Aware Group Unfairness Elimination](https://mlsanity.com/paper/2208.14175/) (2022)
- [Why Are You Wrong? Counterfactual Explanations for Language Grounding with 3D Objects](https://mlsanity.com/paper/2505.06030/) (2025)
- [HEX: Human-in-the-loop Explainability via Deep Reinforcement Learning](https://mlsanity.com/paper/2206.01343/) (2022)
- [CEnt: An Entropy-based Model-agnostic Explainability Framework to Contrast Classifiers' Decisions](https://mlsanity.com/paper/2301.07941/) (2023)
- [Personalized Decision Supports based on Theory of Mind Modeling and Explainable Reinforcement Learning](https://mlsanity.com/paper/2312.08397/) (2023)
- [Improving Decision Sparsity](https://mlsanity.com/paper/2410.20483/) (2024)
- [Model-Free Counterfactual Subset Selection at Scale](https://mlsanity.com/paper/2502.08326/) (2025)
- [Learning Marked Temporal Point Process Explanations based on Counterfactual and Factual Reasoning](https://mlsanity.com/paper/2508.11943/) (2025)
- [An Explainable Gaussian Process Auto-encoder for Tabular Data](https://mlsanity.com/paper/2509.00884/) (2025)

## Abstract (arXiv)

Inverse classification is the process of perturbing an instance in a meaningful way such that it is more likely to conform to a specific class. Historical methods that address such a problem are often framed to leverage only a single classifier, or specific set of classifiers. These works are often accompanied by naive assumptions. In this work we propose generalized inverse classification (GIC), which avoids restricting the classification model that can be used. We incorporate this formulation into a refined framework in which GIC takes place. Under this framework, GIC operates on features that are immediately actionable. Each change incurs an individual cost, either linear or non-linear. Such changes are subjected to occur within a specified level of cumulative change (budget). Furthermore, our framework incorporates the estimation of features that change as a consequence of direct actions taken (indirectly changeable features). To solve such a problem, we propose three real-valued heuristic-based methods and two sensitivity analysis-based comparison methods, each of which is evaluated on two freely available real-world datasets. Our results demonstrate the validity and benefits of our formulation, framework, and methods.