TraCE: Trajectory Counterfactual Explanation Scores
Machine Learning
2024-01-29 v2 Computers and Society
Metric Geometry
Abstract
Counterfactual explanations, and their associated algorithmic recourse, are typically leveraged to understand, explain, and potentially alter a prediction coming from a black-box classifier. In this paper, we propose to extend the use of counterfactuals to evaluate progress in sequential decision making tasks. To this end, we introduce a model-agnostic modular framework, TraCE (Trajectory Counterfactual Explanation) scores, which is able to distill and condense progress in highly complex scenarios into a single value. We demonstrate TraCE's utility across domains by showcasing its main properties in two case studies spanning healthcare and climate change.
Cite
@article{arxiv.2309.15965,
title = {TraCE: Trajectory Counterfactual Explanation Scores},
author = {Jeffrey N. Clark and Edward A. Small and Nawid Keshtmand and Michelle W. L. Wan and Elena Fillola Mayoral and Enrico Werner and Christopher P. Bourdeaux and Raul Santos-Rodriguez},
journal= {arXiv preprint arXiv:2309.15965},
year = {2024}
}
Comments
10 pages, 4 figures, appendix