mlsanityData to 7 Oct 2026

Deep Counterfactual Networks with Propensity-Dropout

arXiv 1706.05966 ↗First posted 19 Jun 2017cs.LG stat.MLcited by 30

Not on the map. Why?

Abstract (arXiv)

We propose a novel approach for inferring the individualized causal effects of a treatment (intervention) from observational data. Our approach conceptualizes causal inference as a multitask learning problem; we model a subject's potential outcomes using a deep multitask network with a set of shared layers among the factual and counterfactual outcomes, and a set of outcome-specific layers. The impact of selection bias in the observational data is alleviated via a propensity-dropout regularization scheme, in which the network is thinned for every training example via a dropout probability that depends on the associated propensity score. The network is trained in alternating phases, where in each phase we use the training examples of one of the two potential outcomes (treated and control populations) to update the weights of the shared layers and the respective outcome-specific layers. Experiments conducted on data based on a real-world observational study show that our algorithm outperforms the state-of-the-art.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 8; 2023: 6; 2024: 5; 2025: 4.

30 papers.

Sort:

  1. 2021On Inductive Biases for Heterogeneous Treatment Effect Estimationcited by 74
  2. 2022Exploring Transformer Backbones for Heterogeneous Treatment Effect Estimationcited by 25
  3. 2022Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimationcited by 21
  4. 2021Estimating Categorical Counterfactuals via Deep Twin Networkscited by 18
  5. 2023Towards Causal Foundation Model: on Duality between Causal Inference and Attentioncited by 17
  6. 2022Adversarial Counterfactual Environment Model Learningcited by 12
  7. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  8. 2022A Survey of Deep Causal Models and Their Industrial Applicationscited by 10
  9. 2025Deep Learning for Time Series Forecasting: A Surveycited by 10
  10. 2021Estimating Potential Outcome Distributions with Collaborating Causal Networkscited by 8
  11. 2023Estimating Causal Effects using a Multi-task Deep Ensemblecited by 7
  12. 2022Covariate-Balancing-Aware Interpretable Deep Learning models for Treatment Effect Estimationcited by 5
18 more
  1. 2021Selecting Treatment Effects Models for Domain Adaptation Using Causal Knowledgecited by 4
  2. 2022Is More Data All You Need? A Causal Explorationcited by 3
  3. 2023Assisting Clinical Decisions for Scarcely Available Treatment via Disentangled Latent Representationcited by 3
  4. 2024Causal Inference with Complex Treatments: A Surveycited by 3
  5. 2021Learning Matching Representations for Individualized Organ Transplantation Allocationcited by 2
  6. 2023DR-VIDAL -- Doubly Robust Variational Information-theoretic Deep Adversarial Learning for Counterfactual Prediction and Treatment Effect Estimation on Real World Datacited by 2
  7. 2021The Bias-Variance Tradeoff of Doubly Robust Estimator with Targeted L1 regularized Neural Networks Predictionscited by 1
  8. 2023A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representationscited by 1
  9. 2024Ads Supply Personalization via Doubly Robust Learningcited by 1
  10. 2025Causal Machine Learning for Surgical Interventionscited by 1
  11. 2021Non parametric estimation of causal populations in a counterfactual scenariocited by 0
  12. 2022TCFimt: Temporal Counterfactual Forecasting from Individual Multiple Treatment Perspectivecited by 0
  13. 2023VLUCI: Variational Learning of Unobserved Confounders for Counterfactual Inferencecited by 0
  14. 2024Enhancing predictive imaging biomarker discovery through treatment effect analysiscited by 0
  15. 2024MSCT: Addressing Time-Varying Confounding with Marginal Structural Causal Transformer for Counterfactual Post-Crash Traffic Predictioncited by 0
  16. 2024Are causal effect estimations enough for optimal recommendations under multitreatment scenarios?cited by 0
  17. 2025Consistent Causal Inference of Group Effects in Non-Targeted Trials with Finitely Many Effect Levelscited by 0
  18. 2025Structure Maintained Representation Learning Neural Network for Causal Inferencecited by 0