# DRTCI: Learning Disentangled Representations for Temporal Causal Inference

arXiv: https://arxiv.org/abs/2201.08137 · HTML: https://mlsanity.com/paper/2201.08137/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 20 Jan 2022.

## Builds on (most cited first, 5 of 5)

- [Learning Representations for Counterfactual Inference](https://mlsanity.com/paper/1605.03661/) (2016)
- [Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations](https://mlsanity.com/paper/2002.04083/) (2020)
- [MetaCI: Meta-Learning for Causal Inference in a Heterogeneous Population](https://mlsanity.com/paper/1912.03960/) (2019)
- [Hi-CI: Deep Causal Inference in High Dimensions](https://mlsanity.com/paper/2008.09858/) (2020)
- [MultiMBNN: Matched and Balanced Causal Inference with Neural Networks](https://mlsanity.com/paper/2004.13446/) (2020)

## Abstract (arXiv)

Medical professionals evaluating alternative treatment plans for a patient often encounter time varying confounders, or covariates that affect both the future treatment assignment and the patient outcome. The recently proposed Counterfactual Recurrent Network (CRN) accounts for time varying confounders by using adversarial training to balance recurrent historical representations of patient data. However, this work assumes that all time varying covariates are confounding and thus attempts to balance the full state representation. Given that the actual subset of covariates that may in fact be confounding is in general unknown, recent work on counterfactual evaluation in the static, non-temporal setting has suggested that disentangling the covariate representation into separate factors, where each either influence treatment selection, patient outcome or both can help isolate selection bias and restrict balancing efforts to factors that influence outcome, allowing the remaining factors which predict treatment without needlessly being balanced.