mlsanityData to 14 Oct 2026

Causality-Encoded Diffusion Models for Interventional Sampling and Edge Inference

arXiv 2604.21843 ↗First posted 23 Apr 2026stat.ME stat.MLcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Standard diffusion models are flexible estimators of complex distributions, but they do not encode causal structures and therefore do not by themselves support causal analysis. We propose a causality-encoded diffusion framework that incorporates a known directed acyclic graph by training conditional diffusion models consistent with the graph factorisation. The resulting sampler approximately recovers the observational distribution and enables interventional sampling by fixing intervened variables while propagating effects through the graph during reverse diffusion. Building on this interventional simulator, we develop a resampling-based test for directed edges that generates null replicates under a candidate graph. We establish convergence guarantees for observational and interventional distribution estimation, with rates governed by the maximum local dimension rather than the ambient dimension, and prove asymptotic control of type I error for the edge test. Simulations show improved interventional distribution recovery relative to baselines, with near-nominal size and favourable power in inference. An application to flow cytometry data demonstrates practical utility of the proposed method in assessing disputed signalling linkages.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 29 of its 52 references that are in the map. First posted on arXiv 23 Apr 2026.

Builds on

29 of 52 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025Score-based Generative Modeling for Conditional Independence Testing29 May
  2. 2024Conditional Diffusion Models Based Conditional Independence Testing16 Dec
  3. 2024Denoising diffusion probabilistic models are optimally adaptive to unknown low dimensionality24 Oct
  4. 2024Linear Convergence of Diffusion Models Under the Manifold Hypothesis11 Oct
  5. 2024O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal Assumptions27 Sep
  6. 2024Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theory18 Mar
  7. 2023Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data14 Feb
  8. 2023Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual Queries2 Feb
  9. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  10. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 19

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  2. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  3. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 211
  4. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  5. 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 140
  6. 2016Panning for Gold: Model-X Knockoffs for High-dimensional Controlled Variable Selectioncited by 121
  7. 2017Approximate Kernel-based Conditional Independence Tests for Fast Non-Parametric Causal Discoverycited by 76
  8. 2023Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvementcited by 49
  9. 2017Model-Powered Conditional Independence Testcited by 43
  10. 2019A simple measure of conditional dependencecited by 38
  11. 2013Cyclic Causal Discovery from Continuous Equilibrium Datacited by 21
  12. 2020Kernel Partial Correlation Coefficient -- a Measure of Conditional Dependencecited by 21
7 more
  1. 2021On boosting the power of Chatterjee's rank correlationcited by 10
  2. 2023Discovery and inference of a causal network with hidden confoundingcited by 8
  3. 2024Enhancing Accuracy in Generative Models via Knowledge Transfercited by 7
  4. 2018Inference in high-dimensional graphical modelscited by 6
  5. 2021Testing Directed Acyclic Graph via Structural, Supervised and Generative Adversarial Learningcited by 4
  6. 2024A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Modelscited by 4
  7. 2022A direct extension of Azadkia & Chatterjee's rank correlation to multi-response vectorscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Smoothing the Landscape: Causal Structure Learning via Diffusion Denoising Objectives
  2. 2024Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand
  3. 2025Diffusion Models in Simulation-Based Inference: A Tutorial Review
  4. 2023Diffusion Model in Causal Inference with Unmeasured Confounders
  5. 2026Scalable Diffusion SBI for Compositional Inference under Simulator Misspecification
  6. 2026Non-parametric recovery of causal diffusion mechanisms from steady-state observations
  7. 2024DiffPO: A causal diffusion model for learning distributions of potential outcomes
  8. 2026Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data