Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference
This work solves the issue of applying causal explanations in complex scenarios for users of SHAP-based explainability, though it is incremental as it builds on existing do-SHAP techniques.
The paper tackled the problem of making do-SHAP explanations practical by addressing its reliance on specific estimands and computational inefficiency, resulting in a method that enables feasible application on complex graphs with significant acceleration and validation on real-world datasets.
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.