# Deconfounding Temporal Autoencoder: Estimating Treatment Effects over Time Using Noisy Proxies

arXiv: https://arxiv.org/abs/2112.03013 · HTML: https://mlsanity.com/paper/2112.03013/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 49 references that are in the map.
- First posted on arXiv 6 Dec 2021.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Learning Representations for Counterfactual Inference](https://mlsanity.com/paper/1605.03661/) (2016)
- [Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes](https://mlsanity.com/paper/1704.02801/) (2017)
- [Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations](https://mlsanity.com/paper/2002.04083/) (2020)
- [MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III](https://mlsanity.com/paper/1907.08322/) (2019)
- [The Blessings of Multiple Causes](https://mlsanity.com/paper/1805.06826/) (2018)
- [Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders](https://mlsanity.com/paper/1902.00450/) (2019)
- [On Inductive Biases for Heterogeneous Treatment Effect Estimation](https://mlsanity.com/paper/2106.03765/) (2021)
- [Causal Inference with Noisy and Missing Covariates via Matrix Factorization](https://mlsanity.com/paper/1806.00811/) (2018)
- [Estimating Average Treatment Effects via Orthogonal Regularization](https://mlsanity.com/paper/2101.08490/) (2021)
- [Sequential Deconfounding for Causal Inference with Unobserved Confounders](https://mlsanity.com/paper/2104.09323/) (2021)
- [Estimating Individual Treatment Effects with Time-Varying Confounders](https://mlsanity.com/paper/2008.13620/) (2020)
- [Generalizing Off-Policy Learning under Sample Selection Bias](https://mlsanity.com/paper/2112.01387/) (2021)
- [AttDMM: An Attentive Deep Markov Model for Risk Scoring in Intensive Care Units](https://mlsanity.com/paper/2102.04702/) (2021)
- [Using Longitudinal Targeted Maximum Likelihood Estimation in Complex Settings with Dynamic Interventions](https://mlsanity.com/paper/1802.05005/) (2018)
- [Targeted Learning with Daily EHR Data](https://mlsanity.com/paper/1705.09874/) (2017)

## Built on by (most cited first, 16 of 16)

- [Causal Transformer for Estimating Counterfactual Outcomes](https://mlsanity.com/paper/2204.07258/) (2022)
- [When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning](https://mlsanity.com/paper/2203.16797/) (2022)
- [Combining Observational and Randomized Data for Estimating Heterogeneous Treatment Effects](https://mlsanity.com/paper/2202.12891/) (2022)
- [Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation](https://mlsanity.com/paper/2310.17463/) (2023)
- [Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders](https://mlsanity.com/paper/2303.02320/) (2023)
- [Counterfactual Generative Models for Time-Varying Treatments](https://mlsanity.com/paper/2305.15742/) (2023)
- [Estimating Conditional Average Treatment Effects with Missing Treatment Information](https://mlsanity.com/paper/2203.01422/) (2022)
- [Causal Contrastive Learning for Counterfactual Regression Over Time](https://mlsanity.com/paper/2406.00535/) (2024)
- [Stabilized Neural Prediction of Potential Outcomes in Continuous Time](https://mlsanity.com/paper/2410.03514/) (2024)
- [Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine](https://mlsanity.com/paper/2204.07124/) (2022)
- [Estimating Treatment Effects in Continuous Time with Hidden Confounders](https://mlsanity.com/paper/2302.09446/) (2023)
- [Detecting User Exits from Online Behavior: A Duration-Dependent Latent State Model](https://mlsanity.com/paper/2208.03937/) (2022)
- [Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data](https://mlsanity.com/paper/2406.06452/) (2024)
- [Combining Incomplete Observational and Randomized Data for Heterogeneous Treatment Effects](https://mlsanity.com/paper/2410.21343/) (2024)
- [A Perspective on Individualized Treatment Effects Estimation from Time-series Health Data](https://mlsanity.com/paper/2402.04668/) (2024)
- [Deconfounded Warm-Start Thompson Sampling with Applications to Precision Medicine](https://mlsanity.com/paper/2505.17283/) (2025)

## Abstract (arXiv)

Estimating individualized treatment effects (ITEs) from observational data is crucial for decision-making. In order to obtain unbiased ITE estimates, a common assumption is that all confounders are observed. However, in practice, it is unlikely that we observe these confounders directly. Instead, we often observe noisy measurements of true confounders, which can serve as valid proxies. In this paper, we address the problem of estimating ITE in the longitudinal setting where we observe noisy proxies instead of true confounders. To this end, we develop the Deconfounding Temporal Autoencoder, a novel method that leverages observed noisy proxies to learn a hidden embedding that reflects the true hidden confounders. In particular, the DTA combines a long short-term memory autoencoder with a causal regularization penalty that renders the potential outcomes and treatment assignment conditionally independent given the learned hidden embedding. Once the hidden embedding is learned via DTA, state-of-the-art outcome models can be used to control for it and obtain unbiased estimates of ITE. Using synthetic and real-world medical data, we demonstrate the effectiveness of our DTA by improving over state-of-the-art benchmarks by a substantial margin.