Consequence-aware Sequential Counterfactual Generation
arXiv:2104.05592 · doi:10.1007/978-3-030-86520-7_42
Abstract
Counterfactuals have become a popular technique nowadays for interacting with black-box machine learning models and understanding how to change a particular instance to obtain a desired outcome from the model. However, most existing approaches assume instant materialization of these changes, ignoring that they may require effort and a specific order of application. Recently, methods have been proposed that also consider the order in which actions are applied, leading to the so-called sequential counterfactual generation problem. In this work, we propose a model-agnostic method for sequential counterfactual generation. We formulate the task as a multi-objective optimization problem and present a genetic algorithm approach to find optimal sequences of actions leading to the counterfactuals. Our cost model considers not only the direct effect of an action, but also its consequences. Experimental results show that compared to state-of-the-art, our approach generates less costly solutions, is more efficient and provides the user with a diverse set of solutions to choose from.
arXiv comment16 pages, 6 figures, Accepted for publication in the research track at ECML-PKDD 2021
References in corpus (10)
- pymoo: Multi-objective Optimization in Python
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
- Actionable Recourse in Linear Classification
- FACE: Feasible and Actionable Counterfactual Explanations
- Multi-Objective Counterfactual Explanations
- Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
- Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
- Generalized Inverse Classification
- A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
- Extracting Incentives from Black-Box Decisions