xai-cola: A Python library for sparsifying counterfactual explanations

TL;DR

xai-cola is a Python library that enhances counterfactual explanations by reducing redundant feature changes, making explanations more concise while maintaining their validity, and it is validated through empirical experiments.

Contribution

It introduces an open-source pipeline for sparsifying counterfactual explanations, compatible with various generators and models, with multiple sparsification policies and visualization tools.

Findings

Produces sparser counterfactuals, reducing feature modifications by up to 50%.

Works with multiple CE generators and models.

Provides visualization routines for analysis and comparison.

Abstract

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.