# Synergizing Deconfounding and Temporal Generalization For Time-series Counterfactual Outcome Estimation

arXiv: https://arxiv.org/abs/2511.16006 · HTML: https://mlsanity.com/paper/2511.16006/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 20 Nov 2025.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Learning Representations for Counterfactual Inference](https://mlsanity.com/paper/1605.03661/) (2016)
- [Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration](https://mlsanity.com/paper/1705.09634/) (2017)
- [Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations](https://mlsanity.com/paper/2002.04083/) (2020)
- [Causal Transformer for Estimating Counterfactual Outcomes](https://mlsanity.com/paper/2204.07258/) (2022)
- [MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III](https://mlsanity.com/paper/1907.08322/) (2019)
- [Theoretical Analysis of Domain Adaptation with Optimal Transport](https://mlsanity.com/paper/1610.04420/) (2016)
- [A Wasserstein-type distance in the space of Gaussian Mixture Models](https://mlsanity.com/paper/1907.05254/) (2019)
- [Time Series Prediction using Deep Learning Methods in Healthcare](https://mlsanity.com/paper/2108.13461/) (2021)
- [Generalization Bounds and Representation Learning for Estimation of Potential Outcomes and Causal Effects](https://mlsanity.com/paper/2001.07426/) (2020)
- [DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Training](https://mlsanity.com/paper/1802.05664/) (2018)
- [Adversarial Balancing-based Representation Learning for Causal Effect Inference with Observational Data](https://mlsanity.com/paper/1904.13335/) (2019)
- [Hierarchical Sliced Wasserstein Distance](https://mlsanity.com/paper/2209.13570/) (2022)
- [DICT-MLM: Improved Multilingual Pre-Training using Bilingual Dictionaries](https://mlsanity.com/paper/2010.12566/) (2020)
- [A Bayesian Nonparametric Approach for Estimating Individualized Treatment-Response Curves](https://mlsanity.com/paper/1608.05182/) (2016)
- [Generative Adversarial Network Training is a Continual Learning Problem](https://mlsanity.com/paper/1811.11083/) (2018)
- [G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes](https://mlsanity.com/paper/2003.10551/) (2020)
- [Transfer Learning for Individual Treatment Effect Estimation](https://mlsanity.com/paper/2210.00380/) (2022)

## Abstract (arXiv)

Estimating counterfactual outcomes from time-series observations is crucial for effective decision-making, e.g. when to administer a life-saving treatment, yet remains significantly challenging because (i) the counterfactual trajectory is never observed and (ii) confounders evolve with time and distort estimation at every step. To address these challenges, we propose a novel framework that synergistically integrates two complementary approaches: Sub-treatment Group Alignment (SGA) and Random Temporal Masking (RTM). Instead of the coarse practice of aligning marginal distributions of the treatments in latent space, SGA uses iterative treatment-agnostic clustering to identify fine-grained sub-treatment groups. Aligning these fine-grained groups achieves improved distributional matching, thus leading to more effective deconfounding. We theoretically demonstrate that SGA optimizes a tighter upper bound on counterfactual risk and empirically verify its deconfounding efficacy. RTM promotes temporal generalization by randomly replacing input covariates with Gaussian noises during training. This encourages the model to rely less on potentially noisy or spuriously correlated covariates at the current step and more on stable historical patterns, thereby improving its ability to generalize across time and better preserve underlying causal relationships. Our experiments demonstrate that while applying SGA and RTM individually improves counterfactual outcome estimation, their synergistic combination consistently achieves state-of-the-art performance. This success comes from their distinct yet complementary roles: RTM enhances temporal generalization and robustness across time steps, while SGA improves deconfounding at each specific time point.