RobustX: Robust Counterfactual Explanations Made Easy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Junqi, Marzari, Luca, Purohit, Aaryan, Leofante, Francesco
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913698788933632
author Jiang, Junqi
Marzari, Luca
Purohit, Aaryan
Leofante, Francesco
author_facet Jiang, Junqi
Marzari, Luca
Purohit, Aaryan
Leofante, Francesco
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_13751
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RobustX: Robust Counterfactual Explanations Made Easy
Jiang, Junqi
Marzari, Luca
Purohit, Aaryan
Leofante, Francesco
Machine Learning
Artificial Intelligence
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.
title RobustX: Robust Counterfactual Explanations Made Easy
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2502.13751