Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909987218915328 |
|---|---|
| author | Parafita, Álvaro Garriga, Tomas Brando, Axel Cazorla, Francisco J. |
| author_facet | Parafita, Álvaro Garriga, Tomas Brando, Axel Cazorla, Francisco J. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_20211 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference Parafita, Álvaro Garriga, Tomas Brando, Axel Cazorla, Francisco J. Machine Learning 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. |
| title | Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.20211 |