mlsanityData to 14 Oct 2026

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

arXiv 2110.14001 ↗First posted 26 Oct 2021cs.LG stat.MLcited by 25

Not on the map. Why?

Abstract (arXiv)

We study the problem of inferring heterogeneous treatment effects from time-to-event data. While both the related problems of (i) estimating treatment effects for binary or continuous outcomes and (ii) predicting survival outcomes have been well studied in the recent machine learning literature, their combination -- albeit of high practical relevance -- has received considerably less attention. With the ultimate goal of reliably estimating the effects of treatments on instantaneous risk and survival probabilities, we focus on the problem of learning (discrete-time) treatment-specific conditional hazard functions. We find that unique challenges arise in this context due to a variety of covariate shift issues that go beyond a mere combination of well-studied confounding and censoring biases. We theoretically analyse their effects by adapting recent generalization bounds from domain adaptation and treatment effect estimation to our setting and discuss implications for model design. We use the resulting insights to propose a novel deep learning method for treatment-specific hazard estimation based on balancing representations. We investigate performance across a range of experimental settings and empirically confirm that our method outperforms baselines by addressing covariate shifts from various sources.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Builds on 32 of its 70 references that are in the map. First posted on arXiv 26 Oct 2021.

Builds on

32 of 70 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Estimation and Inference of Heterogeneous Treatment Effects using Random Forestscited by 600
  3. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 478
  4. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 410
  5. 2017Quasi-Oracle Estimation of Heterogeneous Treatment Effectscited by 332
  6. 2016Learning Representations for Counterfactual Inferencecited by 329
  7. 2016Generalized Random Forestscited by 312
  8. 2019Adapting Neural Networks for the Estimation of Treatment Effectscited by 287
  9. 2015Recursive Partitioning for Heterogeneous Causal Effectscited by 255
  10. 2018What is the Effect of Importance Weighting in Deep Learning?cited by 251
  11. 2013Fast Computation of Wasserstein Barycenterscited by 216
  12. 2017Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processescited by 158
20 more
  1. 2021Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithmscited by 144
  2. 2018An introduction to domain adaptation and transfer learningcited by 112
  3. 2019Support and Invertibility in Domain-Invariant Representationscited by 87
  4. 2021Discussion on "Bayesian Regression Tree Models for Causal Inference: Regularization, Confounding, and Heterogeneous Effects" by Hahn, Murray and Carvalhocited by 77
  5. 2018A Scalable Discrete-Time Survival Model for Neural Networkscited by 72
  6. 2020Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effectscited by 72
  7. 2019Continuous and Discrete-Time Survival Prediction with Neural Networkscited by 70
  8. 2016Deep Survival Analysiscited by 61
  9. 2018Deep Recurrent Survival Analysiscited by 61
  10. 2020Counterfactual Representation Learning with Balancing Weightscited by 45
  11. 2018Learning Weighted Representations for Generalization Across Designscited by 41
  12. 2021Understanding the role of importance weighting for deep learningcited by 39
  13. 2018Adversarial Time-to-Event Modelingcited by 33
  14. 2018Countdown Regression: Sharp and Calibrated Survival Predictionscited by 31
  15. 2020Estimating heterogeneous treatment effects with right-censored data via causal survival forestscited by 29
  16. 2017Deep Learning for Patient-Specific Kidney Graft Survival Analysiscited by 18
  17. 2017Individualized Treatment Effects with Censored Data via Fully Nonparametric Bayesian Accelerated Failure Time Modelscited by 13
  18. 2020Estimating heterogeneous survival treatment effect in observational data using machine learningcited by 12
  19. 2019Deep Learning for Survival Outcomescited by 7
  20. 2017Targeted Learning Ensembles for Optimal Individualized Treatment Rules with Time-to-Event Outcomescited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 6; 2024: 7; 2025: 5; 2026: 2.

25 papers.

Sort:

By area:

  1. 2024Model-agnostic meta-learners for estimating heterogeneous treatment effects over timecited by 19
  2. 2024An Introduction to Deep Survival Analysis Models for Predicting Time-to-Event Outcomescited by 16
  3. 2023Reliable Off-Policy Learning for Dosage Combinationscited by 15
  4. 2023Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Timecited by 15
  5. 2022Counterfactual Phenotyping with Censored Time-to-Eventscited by 13
  6. 2025Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Datacited by 10
  7. 2022To Impute or not to Impute? Missing Data in Treatment Effect Estimationcited by 9
  8. 2022BITES: Balanced Individual Treatment Effect for Survival datacited by 7
  9. 2023Understanding the Impact of Competing Events on Heterogeneous Treatment Effect Estimation from Time-to-Event Datacited by 5
  10. 2025Policy Optimization for Dynamic Heart Transplant Allocationcited by 5
  11. 2024Estimating Heterogeneous Treatment Effects on Survival Outcomes Using Counterfactual Censoring Unbiased Transformationscited by 4
  12. 2024Benchmarking Observational Studies with Experimental Data under Right-Censoringcited by 4
13 more
  1. 2024Toward a Well-Calibrated Discrimination via Survival Outcome-Aware Contrastive Learningcited by 4
  2. 2022Heterogeneous Treatment Effect Estimation for Observational Data using Model-based Forestscited by 3
  3. 2024Towards Representation Learning for Weighting Problems in Design-Based Causal Inferencecited by 2
  4. 2022BENK: The Beran Estimator with Neural Kernels for Estimating the Heterogeneous Treatment Effectcited by 1
  5. 2023Recovering Sparse and Interpretable Subgroups with Heterogeneous Treatment Effects with Censored Time-to-Event Outcomescited by 1
  6. 2025Assessing the robustness of heterogeneous treatment effects in survival analysis under informative censoringcited by 1
  7. 2025Dual Mixture-of-Experts Framework for Discrete-Time Survival Analysiscited by 1
  8. 2026Stable Time Series Prediction of Enterprise Carbon Emissions Based on Causal Inferencecited by 1
  9. 2023Counterfactual Outcome Prediction using Structured State Space Modelcited by 0
  10. 2023A Stable and Efficient Covariate-Balancing Estimator for Causal Survival Effectscited by 0
  11. 2024Identifying treatment response subgroups in observational time-to-event datacited by 0
  12. 2025CAST: Time-Varying Treatment Effects with Application to Chemotherapy and Radiotherapy on Head and Neck Squamous Cell Carcinomacited by 0
  13. 2026Estimating heterogeneous treatment effects with survival outcomes via a deep survival learnercited by 0