mlsanityData to 14 Oct 2026

Counterfactual Generative Models for Time-Varying Treatments

arXiv 2305.15742 ↗First posted 25 May 2023stat.ML cs.LG stat.MEcited by 17

Not on the map. Why?

Abstract (arXiv)

Estimating the counterfactual outcome of treatment is essential for decision-making in public health and clinical science, among others. Often, treatments are administered in a sequential, time-varying manner, leading to an exponentially increased number of possible counterfactual outcomes. Furthermore, in modern applications, the outcomes are high-dimensional and conventional average treatment effect estimation fails to capture disparities in individuals. To tackle these challenges, we propose a novel conditional generative framework capable of producing counterfactual samples under time-varying treatment, without the need for explicit density estimation. Our method carefully addresses the distribution mismatch between the observed and counterfactual distributions via a loss function based on inverse probability re-weighting, and supports integration with state-of-the-art conditional generative models such as the guided diffusion and conditional variational autoencoder. We present a thorough evaluation of our method using both synthetic and real-world data. Our results demonstrate that our method is capable of generating high-quality counterfactual samples and outperforms the state-of-the-art baselines.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 44 of its 115 references that are in the map. First posted on arXiv 25 May 2023.

Builds on

44 of 115 references.

References · 44

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  8. 2014Conditional Generative Adversarial Netscited by 2,162
  9. 2021Variational Diffusion Modelscited by 1,153
  10. 2019An Introduction to Variational Autoencoderscited by 1,000
  11. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 410
  12. 2018Statistical Aspects of Wasserstein Distancescited by 203
32 more
  1. 2015Learning with a Wasserstein Losscited by 196
  2. 2017Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processescited by 158
  3. 2020Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representationscited by 155
  4. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 123
  5. 2021Counterfactual Generative Networkscited by 111
  6. 2022AUC Maximization in the Era of Big Data and AI: A Surveycited by 100
  7. 2018Molecular generative model based on conditional variational autoencoder for de novo molecular designcited by 73
  8. 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
  9. 2022Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equationscited by 59
  10. 2021Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confoundingcited by 50
  11. 2020RealCause: Realistic Causal Inference Benchmarkingcited by 46
  12. 2020Counterfactual Representation Learning with Balancing Weightscited by 45
  13. 2021Semiparametric counterfactual density estimationcited by 42
  14. 2019Conditional Flow Variational Autoencoders for Structured Sequence Predictioncited by 37
  15. 2022Estimating average causal effects from patient trajectoriescited by 29
  16. 2021Conditional Generative Models for Counterfactual Explanationscited by 28
  17. 2022D'ARTAGNAN: Counterfactual Video Generationcited by 28
  18. 2022Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimationcited by 25
  19. 2017Causal Generative Neural Networkscited by 24
  20. 2022Normalizing Flows for Interventional Density Estimationcited by 21
  21. 2018Conditional Variational Autoencoder for Neural Machine Translationcited by 20
  22. 2022Validating Causal Inference Methodscited by 20
  23. 2022Partial Identification of Treatment Effects with Implicit Generative Modelscited by 17
  24. 2018Causal effects based on distributional distancescited by 16
  25. 2021Deconfounding Temporal Autoencoder: Estimating Treatment Effects over Time Using Noisy Proxiescited by 16
  26. 2022Estimating counterfactual treatment outcomes over time in complex multiagent scenarioscited by 12
  27. 2021Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Timecited by 9
  28. 2021Causal Effect Variational Autoencoder with Uniform Treatmentcited by 8
  29. 2021Early Detection of COVID-19 Hotspots Using Spatio-Temporal Datacited by 3
  30. 2022CausalEGM: a general causal inference framework by encoding generative modelingcited by 3
  31. 2022Flexible Triggering Kernels for Hawkes Process Modelingcited by 2
  32. 2021Causal Inference in the Time of Covid-19cited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 5; 2026: 6.

17 papers.

Sort:

By area:

  1. 2025Gen-DFL: Decision-Focused Generative Learning for Robust Decision Makingcited by 18
  2. 2024IGC-Net for conditional average potential outcome estimation over timecited by 10
  3. 2025DoubleGen: Debiased Generative Modeling of Counterfactualscited by 9
  4. 2024Causal Contrastive Learning for Counterfactual Regression Over Timecited by 7
  5. 2025Transformer-Based Spatial-Temporal Counterfactual Outcomes Estimationcited by 4
  6. 2025DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Seriescited by 4
  7. 2024Balancing Optimality and Diversity: Human-Centered Decision Making through Generative Curationcited by 2
  8. 2024Recurrent Neural Goodness-of-Fit Test for Time Seriescited by 2
  9. 2024New User Event Prediction Through the Lens of Causal Inferencecited by 1
  10. 2025GDR-learners: Orthogonal Learning of Generative Models for Potential Outcomescited by 1
  11. 2026Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Datacited by 1
  12. 2026What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditionscited by 1
5 more
  1. 2024Distance-Preserving Representations for Genomic Spatial Reconstructioncited by 0
  2. 2026From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Predictioncited by 0
  3. 2026Benchmarking Counterfactual Prediction in Epidemic Time Series with Time-Varying Interventionscited by 0
  4. 2026Are Good Generators Good Decision-Makers? Policy Learning for General Interventions via Retargeted Counterfactual Generationcited by 0
  5. 2026Chance-constrained selection of sequential intervention strategies from counterfactual estimatescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Debiased Counterfactual Generation via Flow Matching from Observations
  2. 2025Flow-based Generative Modeling of Potential Outcomes and Counterfactuals
  3. 2026OrthoGen: A Generative Orthogonal Learner for Time-Varying Treatments
  4. 2024Ablation Based Counterfactuals
  5. 2026Generating Chest X-Ray Counterfactuals by Specialising Foundation Image Models
  6. 2026DeepImagine: Clinical Trial Outcome Prediction via Stepwise Local Counterfactual Imaginations
  7. 2024DiffusionCounterfactuals: Inferring High-dimensional Counterfactuals with Guidance of Causal Representations
  8. 2026Generating Medical Image Counterfactuals using Causal Explanations