Practical Do-Shapley Explanations with Estimand-Agnostic Causal Inference

Abstract

Among explainability techniques, SHAP stands out as one of the most popular, but often overlooks the causal structure of the problem. In response, do-SHAP employs interventional queries, but its reliance on estimands hinders its practical application. To address this problem, we propose the use of estimand-agnostic approaches, which allow for the estimation of any identifiable query from a single model, making do-SHAP feasible on complex graphs. We also develop a novel algorithm to significantly accelerate its computation at a negligible cost, as well as a method to explain inaccessible Data Generating Processes. We demonstrate the estimation and computational performance of our approach, and validate it on two real-world datasets, highlighting its potential in obtaining reliable explanations.

Cite

Text

Parafita et al. "Practical Do-Shapley Explanations with Estimand-Agnostic Causal Inference." Advances in Neural Information Processing Systems, 2025.

Markdown

[Parafita et al. "Practical Do-Shapley Explanations with Estimand-Agnostic Causal Inference." Advances in Neural Information Processing Systems, 2025.](https://mlanthology.org/neurips/2025/parafita2025neurips-practical/)

BibTeX

@inproceedings{parafita2025neurips-practical,
  title     = {{Practical Do-Shapley Explanations with Estimand-Agnostic Causal Inference}},
  author    = {Parafita, Álvaro and Garriga, Tomas and Brando, Axel and Cazorla, Francisco J.},
  booktitle = {Advances in Neural Information Processing Systems},
  year      = {2025},
  url       = {https://mlanthology.org/neurips/2025/parafita2025neurips-practical/}
}