Flexible Counterfactual Explanations with Generative Models
This addresses the need for personalized counterfactual explanations for users with heterogeneous real-world constraints, representing an incremental improvement over existing methods.
The paper tackled the problem of inflexible counterfactual explanations by introducing a framework that allows users to dynamically specify mutable features at inference time, resulting in significantly improved validity compared to traditional benchmark methods across economic and healthcare datasets.
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.