A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability
Abstract
Counterfactual explanations enhance interpretability by identifying alternative inputs that produce different outputs, offering localized insights into model decisions. However, traditional methods often neglect causal relationships, leading to unrealistic examples. While newer approaches integrate causality, they are computationally expensive. To address these challenges, we propose an efficient method called BRACE based on backtracking counterfactuals that incorporates causal reasoning to generate actionable explanations. We first examine the limitations of existing methods and then introduce our novel approach and its features. We also explore the relationship between our method and previous techniques, demonstrating that it generalizes them in specific scenarios. Finally, experiments show that our method provides deeper insights into model outputs.
Cite
Text
Fatemi et al. "A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability." Proceedings of the 42nd International Conference on Machine Learning, 2025.Markdown
[Fatemi et al. "A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability." Proceedings of the 42nd International Conference on Machine Learning, 2025.](https://mlanthology.org/icml/2025/fatemi2025icml-new/)BibTeX
@inproceedings{fatemi2025icml-new,
title = {{A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability}},
author = {Fatemi, Pouria and Sharifian, Ehsan and Yassaee, Mohammad Hossein},
booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
year = {2025},
pages = {16273-16285},
volume = {267},
url = {https://mlanthology.org/icml/2025/fatemi2025icml-new/}
}