mlsanityData to 14 Oct 2026

Counterfactual Probabilistic Diffusion with Expert Models

arXiv 2508.13355 ↗First posted 18 Aug 2025cs.LG cs.AI stat.MEcited by 4

Not on the map. Why?

Abstract (arXiv)

Predicting counterfactual distributions in complex dynamical systems is essential for scientific modeling and decision-making in domains such as public health and medicine. However, existing methods often rely on point estimates or purely data-driven models, which tend to falter under data scarcity. We propose a time series diffusion-based framework that incorporates guidance from imperfect expert models by extracting high-level signals to serve as structured priors for generative modeling. Our method, ODE-Diff, bridges mechanistic and data-driven approaches, enabling more reliable and interpretable causal inference. We evaluate ODE-Diff across semi-synthetic COVID-19 simulations, synthetic pharmacological dynamics, and real-world case studies, demonstrating that it consistently outperforms strong baselines in both point prediction and distributional accuracy.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 32 of its 81 references that are in the map. First posted on arXiv 18 Aug 2025.

Builds on

32 of 81 references.

References · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  4. 2018Neural Ordinary Differential Equationscited by 3,779
  5. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 506
  6. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 478
  7. 2019Augmented Neural ODEscited by 397
  8. 2017Quasi-Oracle Estimation of Heterogeneous Treatment Effectscited by 332
  9. 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generationcited by 184
  10. 2020Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representationscited by 155
  11. 2021Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithmscited by 144
  12. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 123
20 more
  1. 2020Causal Autoregressive Flowscited by 99
  2. 2020Augmenting Physical Models with Deep Networks for Complex Dynamics Forecastingcited by 95
  3. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  4. 2024Causal machine learning for predicting treatment outcomescited by 74
  5. 2020Treatment effect estimation with disentangled latent factorscited by 63
  6. 2022Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equationscited by 59
  7. 2021Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progressioncited by 48
  8. 2014From Ordinary Differential Equations to Structural Causal Models: the deterministic casecited by 41
  9. 2023Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesiscited by 32
  10. 2023Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Imagescited by 30
  11. 2023Modeling Causal Mechanisms with Diffusion Models for Interventional and Counterfactual Queriescited by 24
  12. 2021VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queriescited by 19
  13. 2023DiffTAD: Temporal Action Detection with Proposal Denoising Diffusioncited by 19
  14. 2024DiffPO: A causal diffusion model for learning distributions of potential outcomescited by 17
  15. 2018Causal effects based on distributional distancescited by 16
  16. 2021ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equationscited by 15
  17. 2020When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processescited by 14
  18. 2021Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Timecited by 9
  19. 2023TS-Diffusion: Generating Highly Complex Time Series with Diffusion Modelscited by 6
  20. 2024SpecSTG: A Fast Spectral Diffusion Framework for Probabilistic Spatio-Temporal Traffic Forecastingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomescited by 1
  2. 2026What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditionscited by 1
  3. 2026Benchmarking Counterfactual Prediction in Epidemic Time Series with Time-Varying Interventionscited by 0
  4. 2026OrthoGen: A Generative Orthogonal Learner for Time-Varying Treatmentscited by 0