mlsanityData to 7 Oct 2026

Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations

arXiv 2002.04083 ↗First posted 10 Feb 2020cs.LG stat.MLcited by 154

Not on the map. Why?

Abstract (arXiv)

Identifying when to give treatments to patients and how to select among multiple treatments over time are important medical problems with a few existing solutions. In this paper, we introduce the Counterfactual Recurrent Network (CRN), a novel sequence-to-sequence model that leverages the increasingly available patient observational data to estimate treatment effects over time and answer such medical questions. To handle the bias from time-varying confounders, covariates affecting the treatment assignment policy in the observational data, CRN uses domain adversarial training to build balancing representations of the patient history. At each timestep, CRN constructs a treatment invariant representation which removes the association between patient history and treatment assignments and thus can be reliably used for making counterfactual predictions. On a simulated model of tumour growth, with varying degree of time-dependent confounding, we show how our model achieves lower error in estimating counterfactuals and in choosing the correct treatment and timing of treatment than current state-of-the-art methods.

Key facts. Cited by 154 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 23; 2023: 30; 2024: 25; 2025: 22; 2026: 40.

154 papers.

Sort:

By area:

  1. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 121
  2. 2022Deep End-to-end Causal Inferencecited by 93
  3. 2024Causal machine learning for predicting treatment outcomescited by 73
  4. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  5. 2022Causal Machine Learning for Healthcare and Precision Medicinecited by 68
  6. 2022Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equationscited by 59
  7. 2022Estimating average causal effects from patient trajectoriescited by 29
  8. 2023Bayesian Neural Controlled Differential Equations for Treatment Effect Estimationcited by 26
  9. 2022Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimationcited by 25
  10. 2021Sequential Deconfounding for Causal Inference with Unobserved Confounderscited by 24
  11. 2023Sharp Bounds for Generalized Causal Sensitivity Analysiscited by 24
  12. 2022Predicting the impact of treatments over time with uncertainty aware neural differential equationscited by 23
38 more
  1. 2022Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimationcited by 21
  2. 2022Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Mediacited by 20
  3. 2023Causal Deep Learningcited by 20
  4. 2023Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimationcited by 20
  5. 2021Policy Analysis using Synthetic Controls in Continuous-Timecited by 18
  6. 2024Model-agnostic meta-learners for estimating heterogeneous treatment effects over timecited by 18
  7. 2022Estimating individual treatment effects under unobserved confounding using binary instrumentscited by 17
  8. 2023Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounderscited by 17
  9. 2023Counterfactual Generative Models for Time-Varying Treatmentscited by 17
  10. 2024DiffPO: A causal diffusion model for learning distributions of potential outcomescited by 17
  11. 2021Deconfounding Temporal Autoencoder: Estimating Treatment Effects over Time Using Noisy Proxiescited by 16
  12. 2023CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systemscited by 16
  13. 2023Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Timecited by 14
  14. 2024Automatically Learning Hybrid Digital Twins of Dynamical Systemscited by 13
  15. 2021Neural Pharmacodynamic State Space Modelingcited by 12
  16. 2021CausalMTA: Eliminating the User Confounding Bias for Causal Multi-touch Attributioncited by 12
  17. 2023Deep Learning based Forecasting: a case study from the online fashion industrycited by 12
  18. 2023Clairvoyance: A Pipeline Toolkit for Medical Time Seriescited by 12
  19. 2024ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inferencecited by 12
  20. 2021The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulationcited by 11
  21. 2022Estimating counterfactual treatment outcomes over time in complex multiagent scenarioscited by 11
  22. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  23. 2022A Survey of Deep Causal Models and Their Industrial Applicationscited by 10
  24. 2023Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysiscited by 10
  25. 2023Instrumental Variable Estimation for Causal Inference in Longitudinal Data with Time-Dependent Latent Confounderscited by 10
  26. 2023Adversarially Balanced Representation for Continuous Treatment Effect Estimationcited by 10
  27. 2024Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformercited by 10
  28. 2024IGC-Net for conditional average potential outcome estimation over timecited by 10
  29. 2025Deep Learning for Time Series Forecasting: A Surveycited by 10
  30. 2021Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Timecited by 9
  31. 2022Adversarial De-confounding in Individualised Treatment Effects Estimationcited by 9
  32. 2022TILDE-Q: A Transformation Invariant Loss Function for Time-Series Forecastingcited by 8
  33. 2023Clinical Decision Transformer: Intended Treatment Recommendation through Goal Promptingcited by 8
  34. 2024Causal Graph ODE: Continuous Treatment Effect Modeling in Multi-agent Dynamical Systemscited by 8
  35. 2024G-Transformer: Counterfactual Outcome Prediction under Dynamic and Time-varying Treatment Regimescited by 8
  36. 2024A Fixed-Point Approach for Causal Generative Modelingcited by 7
  37. 2024Causal Contrastive Learning for Counterfactual Regression Over Timecited by 7
  38. 2024Stabilized Neural Prediction of Potential Outcomes in Continuous Timecited by 7

50 most cited of 154 All 154 (JSON)