xai-cola: A Python library for sparsifying counterfactual explanations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Lin, You, Lei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908852200407040
author Zhu, Lin
You, Lei
author_facet Zhu, Lin
You, Lei
contents Counterfactual explanation (CE) is an important domain within post-hoc explainability. However, the explanations generated by most CE generators are often highly redundant. This work introduces an open-source Python library xai-cola, which provides an end-to-end pipeline for sparsifying CEs produced by arbitrary generators, reducing superfluous feature changes while preserving their validity. It offers a documented API that takes as input raw tabular data in pandas DataFrame form, a preprocessing object (for standardization and encoding), and a trained scikit-learn or PyTorch model. On this basis, users can either employ the built-in or externally imported CE generators. The library also implements several sparsification policies and includes visualization routines for analysing and comparing sparsified counterfactuals. xai-cola is released under the MIT license and can be installed from PyPI. Empirical experiments indicate that xai-cola produces sparser counterfactuals across several CE generators, reducing the number of modified features by up to 50% in our setting. The source code is available at https://github.com/understanding-ml/COLA.
format Preprint
id arxiv_https___arxiv_org_abs_2602_21845
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle xai-cola: A Python library for sparsifying counterfactual explanations
Zhu, Lin
You, Lei
Machine Learning
Artificial Intelligence
Computers and Society
Counterfactual explanation (CE) is an important domain within post-hoc explainability. However, the explanations generated by most CE generators are often highly redundant. This work introduces an open-source Python library xai-cola, which provides an end-to-end pipeline for sparsifying CEs produced by arbitrary generators, reducing superfluous feature changes while preserving their validity. It offers a documented API that takes as input raw tabular data in pandas DataFrame form, a preprocessing object (for standardization and encoding), and a trained scikit-learn or PyTorch model. On this basis, users can either employ the built-in or externally imported CE generators. The library also implements several sparsification policies and includes visualization routines for analysing and comparing sparsified counterfactuals. xai-cola is released under the MIT license and can be installed from PyPI. Empirical experiments indicate that xai-cola produces sparser counterfactuals across several CE generators, reducing the number of modified features by up to 50% in our setting. The source code is available at https://github.com/understanding-ml/COLA.
title xai-cola: A Python library for sparsifying counterfactual explanations
topic Machine Learning
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2602.21845