RobustX: Robust Counterfactual Explanations Made Easy

TL;DR

RobustX is an open-source Python library designed to generate and evaluate robust counterfactual explanations for machine learning models, addressing the need for explainability and robustness in high-stakes decision-making.

Contribution

The paper introduces RobustX, a comprehensive library that standardizes and facilitates the development and comparison of robust counterfactual explanation methods.

Findings

Provides a collection of state-of-the-art CE methods

Enables benchmarking of robustness in explanations

Supports easy extension for new methods

Abstract

The increasing use of Machine Learning (ML) models to aid decision-making in high-stakes industries demands explainability to facilitate trust. Counterfactual Explanations (CEs) are ideally suited for this, as they can offer insights into the predictions of an ML model by illustrating how changes in its input data may lead to different outcomes. However, for CEs to realise their explanatory potential, significant challenges remain in ensuring their robustness under slight changes in the scenario being explained. Despite the widespread recognition of CEs' robustness as a fundamental requirement, a lack of standardised tools and benchmarks hinders a comprehensive and effective comparison of robust CE generation methods. In this paper, we introduce RobustX, an open-source Python library implementing a collection of CE generation and evaluation methods, with a focus on the robustness property. RobustX provides interfaces to several existing methods from the literature, enabling streamlined access to state-of-the-art techniques. The library is also easily extensible, allowing fast prototyping of novel robust CE generation and evaluation methods.