# Invariant Representation Learning for Treatment Effect Estimation

arXiv: https://arxiv.org/abs/2011.12379 · HTML: https://mlsanity.com/paper/2011.12379/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2020.

## Built on by (most cited first, 25 of 25)

- [Desiderata for Representation Learning: A Causal Perspective](https://mlsanity.com/paper/2109.03795/) (2021)
- [Causal Effect Inference for Structured Treatments](https://mlsanity.com/paper/2106.01939/) (2021)
- [Provable Domain Generalization via Invariant-Feature Subspace Recovery](https://mlsanity.com/paper/2201.12919/) (2022)
- [Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation](https://mlsanity.com/paper/2210.06183/) (2022)
- [Causal Deep Learning](https://mlsanity.com/paper/2303.02186/) (2023)
- [Causal Evaluation of Language Models](https://mlsanity.com/paper/2405.00622/) (2024)
- [Optimization-based Causal Estimation from Heterogenous Environments](https://mlsanity.com/paper/2109.11990/) (2021)
- [Data Augmentations for Improved (Large) Language Model Generalization](https://mlsanity.com/paper/2310.12803/) (2023)
- [Long-term Causal Effects Estimation via Latent Surrogates Representation Learning](https://mlsanity.com/paper/2208.04589/) (2022)
- [Meta-Learners for Partially-Identified Treatment Effects Across Multiple Environments](https://mlsanity.com/paper/2406.02464/) (2024)
- [On Invariance Penalties for Risk Minimization](https://mlsanity.com/paper/2106.09777/) (2021)
- [Finding Valid Adjustments under Non-ignorability with Minimal DAG Knowledge](https://mlsanity.com/paper/2106.11560/) (2021)
- [Generalization bounds and algorithms for estimating conditional average treatment effect of dosage](https://mlsanity.com/paper/2205.14692/) (2022)
- [An Invariant Learning Characterization of Controlled Text Generation](https://mlsanity.com/paper/2306.00198/) (2023)
- [Scalable and Flexible Causal Discovery with an Efficient Test for Adjacency](https://mlsanity.com/paper/2406.09177/) (2024)
- [Matched sample selection with GANs for mitigating attribute confounding](https://mlsanity.com/paper/2103.13455/) (2021)
- [Causal Inference with Latent Variables: Recent Advances and Future Prospectives](https://mlsanity.com/paper/2406.13966/) (2024)
- [Conditionally Invariant Representation Learning for Disentangling Cellular Heterogeneity](https://mlsanity.com/paper/2307.00558/) (2023)
- [Local Learning for Covariate Selection in Nonparametric Causal Effect Estimation with Latent Variables](https://mlsanity.com/paper/2411.16315/) (2024)
- [Meta-learning for heterogeneous treatment effect estimation with closed-form solvers](https://mlsanity.com/paper/2305.11353/) (2023)
- [Causal Effect Identification in Heterogeneous Environments from Higher-Order Moments](https://mlsanity.com/paper/2506.11756/) (2025)
- [Invariant-Feature Subspace Recovery: A New Class of Provable Domain Generalization Algorithms](https://mlsanity.com/paper/2311.00966/) (2023)
- [Multi-environment Topic Models](https://mlsanity.com/paper/2410.24126/) (2024)
- [Diversity Boosted Learning for Domain Generalization with Large Number of Domains](https://mlsanity.com/paper/2207.13865/) (2022)
- [Testing Generalizability in Causal Inference](https://mlsanity.com/paper/2411.03021/) (2024)

## Abstract (arXiv)

The defining challenge for causal inference from observational data is the presence of `confounders', covariates that affect both treatment assignment and the outcome. To address this challenge, practitioners collect and adjust for the covariates, hoping that they adequately correct for confounding. However, including every observed covariate in the adjustment runs the risk of including `bad controls', variables that induce bias when they are conditioned on. The problem is that we do not always know which variables in the covariate set are safe to adjust for and which are not. To address this problem, we develop Nearly Invariant Causal Estimation (NICE). NICE uses invariant risk minimization (IRM) [Arj19] to learn a representation of the covariates that, under some assumptions, strips out bad controls but preserves sufficient information to adjust for confounding. Adjusting for the learned representation, rather than the covariates themselves, avoids the induced bias and provides valid causal inferences. We evaluate NICE on both synthetic and semi-synthetic data. When the covariates contain unknown collider variables and other bad controls, NICE performs better than adjusting for all the covariates.