CARE: Coherent Actionable Recourse based on Sound Counterfactual Explanations

TL;DR

CARE is a modular framework that generates diverse, coherent, and actionable counterfactual explanations for black-box models, integrating domain knowledge and user constraints through multi-objective optimization.

Contribution

It introduces a novel, model-agnostic approach for producing sound, coherent, and customizable counterfactual explanations and recourse, addressing key interpretability and actionability challenges.

Findings

Outperforms baseline methods in generating effective counterfactuals

Produces diverse and coherent explanations respecting user constraints

Demonstrates effectiveness on standard datasets and black-box models

Abstract

Counterfactual explanation methods interpret the outputs of a machine learning model in the form of "what-if scenarios" without compromising the fidelity-interpretability trade-off. They explain how to obtain a desired prediction from the model by recommending small changes to the input features, aka recourse. We believe an actionable recourse should be created based on sound counterfactual explanations originating from the distribution of the ground-truth data and linked to the domain knowledge. Moreover, it needs to preserve the coherency between changed/unchanged features while satisfying user/domain-specified constraints. This paper introduces CARE, a modular explanation framework that addresses the model- and user-level desiderata in a consecutive and structured manner. We tackle the existing requirements by proposing novel and efficient solutions that are formulated in a multi-objective optimization framework. The designed framework enables including arbitrary requirements and generating counterfactual explanations and actionable recourse by choice. As a model-agnostic approach, CARE generates multiple, diverse explanations for any black-box model in tabular classification and regression settings. Several experiments on standard data sets and black-box models demonstrate the effectiveness of our modular framework and its superior performance compared to the baselines.