mlsanityData to 14 Oct 2026

Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference

arXiv 2509.20211 ↗First posted 24 Sep 2025cs.LGcited by 6

Not on the map. Why?

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.

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

23 of 46 references.

References · 23

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  6. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  7. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
  8. 2019Neural Spline Flowscited by 596
  9. 2020A Survey on Neural Network Interpretabilitycited by 291
  10. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 211
  11. 2019Feature relevance quantification in explainable AI: A causal problemcited by 167
  12. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
11 more
  1. 2022Algorithms to estimate Shapley value feature attributionscited by 115
  2. 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
  3. 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
  4. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 98
  5. 2020Shapley Flow: A Graph-based Approach to Interpreting Model Predictionscited by 51
  6. 2023Causal normalizing flows: from theory to practicecited by 51
  7. 2022Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNetcited by 41
  8. 2018Identifying Causal Effects with the R Package causaleffectcited by 19
  9. 2019Explaining Visual Models by Causal Attributioncited by 18
  10. 2023Efficient SAGE Estimation via Causal Structure Learningcited by 4
  11. 2021Algorithmic Causal Effect Identification with causaleffectcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Exactly Computing do-Shapley Valuescited by 3
  2. 2026cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Contextcited by 0
  3. 2026ConfoundingSHAP: Quantifying confounding strength in causal inferencecited by 0
  4. 2026Decision-Aware Proximal Bridge Learning for Optimal Treatment Selectioncited by 0
  5. 2026Feature Attribution in Directed Acyclic Graphs Using Edge Interventioncited by 0
  6. 2026FinInvest-GTCN: Explainable Graph-Temporal-Causal Modeling for Risk-Aware Investment Decision Optimizationcited by 0