# Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference

arXiv: https://arxiv.org/abs/2509.20211 · HTML: https://mlsanity.com/paper/2509.20211/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 46 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 23 of 23)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [Normalizing Flows for Probabilistic Modeling and Inference](https://mlsanity.com/paper/1912.02762/) (2019)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Neural Spline Flows](https://mlsanity.com/paper/1906.04032/) (2019)
- [A Survey on Neural Network Interpretability](https://mlsanity.com/paper/2012.14261/) (2020)
- [Deep Structural Causal Models for Tractable Counterfactual Inference](https://mlsanity.com/paper/2006.06485/) (2020)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training](https://mlsanity.com/paper/1709.02023/) (2017)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models](https://mlsanity.com/paper/2011.01625/) (2020)
- [The Causal-Neural Connection: Expressiveness, Learnability, and Inference](https://mlsanity.com/paper/2107.00793/) (2021)
- [Shapley Flow: A Graph-based Approach to Interpreting Model Predictions](https://mlsanity.com/paper/2010.14592/) (2020)
- [Causal normalizing flows: from theory to practice](https://mlsanity.com/paper/2306.05415/) (2023)
- [Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet](https://mlsanity.com/paper/2212.04871/) (2022)
- [Identifying Causal Effects with the R Package causaleffect](https://mlsanity.com/paper/1806.07161/) (2018)
- [Explaining Visual Models by Causal Attribution](https://mlsanity.com/paper/1909.08891/) (2019)
- [Efficient SAGE Estimation via Causal Structure Learning](https://mlsanity.com/paper/2304.03113/) (2023)
- [Algorithmic Causal Effect Identification with causaleffect](https://mlsanity.com/paper/2107.04632/) (2021)

## Built on by (most cited first, 6 of 6)

- [Exactly Computing do-Shapley Values](https://mlsanity.com/paper/2602.07203/) (2026)
- [cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context](https://mlsanity.com/paper/2602.20396/) (2026)
- [ConfoundingSHAP: Quantifying confounding strength in causal inference](https://mlsanity.com/paper/2605.10533/) (2026)
- [Decision-Aware Proximal Bridge Learning for Optimal Treatment Selection](https://mlsanity.com/paper/2605.16989/) (2026)
- [Feature Attribution in Directed Acyclic Graphs Using Edge Intervention](https://mlsanity.com/paper/2606.15273/) (2026)
- [FinInvest-GTCN: Explainable Graph-Temporal-Causal Modeling for Risk-Aware Investment Decision Optimization](https://mlsanity.com/paper/2606.28933/) (2026)

## Abstract (arXiv)

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.