Flexible Counterfactual Explanations with Generative Models

TL;DR

This paper introduces FCEGAN, a flexible, user-driven framework for generating counterfactual explanations using generative models, which adapts to user constraints and works in black-box scenarios, improving explanation validity.

Contribution

The paper presents a novel framework that allows dynamic specification of mutable features via counterfactual templates, enabling personalized explanations without retraining or extra optimization.

Findings

FCEGAN outperforms traditional methods in explanation validity.

It effectively incorporates user constraints into counterfactuals.

The approach works in black-box model scenarios.

Abstract

Counterfactual explanations provide actionable insights to achieve desired outcomes by suggesting minimal changes to input features. However, existing methods rely on fixed sets of mutable features, which makes counterfactual explanations inflexible for users with heterogeneous real-world constraints. Here, we introduce Flexible Counterfactual Explanations, a framework incorporating counterfactual templates, which allows users to dynamically specify mutable features at inference time. In our implementation, we use Generative Adversarial Networks (FCEGAN), which align explanations with user-defined constraints without requiring model retraining or additional optimization. Furthermore, FCEGAN is designed for black-box scenarios, leveraging historical prediction datasets to generate explanations without direct access to model internals. Experiments across economic and healthcare datasets demonstrate that FCEGAN significantly improves counterfactual explanations' validity compared to traditional benchmark methods. By integrating user-driven flexibility and black-box compatibility, counterfactual templates support personalized explanations tailored to user constraints.