# Learning Disentangled Representations for Counterfactual Regression via Mutual Information Minimization

arXiv: https://arxiv.org/abs/2206.01022 · HTML: https://mlsanity.com/paper/2206.01022/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 2 Jun 2022.

## Builds on (most cited first, 9 of 9)

- [Learning Representations for Counterfactual Inference](https://mlsanity.com/paper/1605.03661/) (2016)
- [Recursive Partitioning for Heterogeneous Causal Effects](https://mlsanity.com/paper/1504.01132/) (2015)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Causal Intervention for Leveraging Popularity Bias in Recommendation](https://mlsanity.com/paper/2105.06067/) (2021)
- [Treatment effect estimation with disentangled latent factors](https://mlsanity.com/paper/2001.10652/) (2020)
- [A unified survey of treatment effect heterogeneity modeling and uplift modeling](https://mlsanity.com/paper/2007.12769/) (2020)
- [Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound](https://mlsanity.com/paper/1811.11979/) (2018)
- [Treatment Targeting by AUUC Maximization with Generalization Guarantees](https://mlsanity.com/paper/2012.09897/) (2020)

## Built on by (most cited first, 19 of 19)

- [Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction](https://mlsanity.com/paper/2401.01646/) (2024)
- [Optimal Transport for Treatment Effect Estimation](https://mlsanity.com/paper/2310.18286/) (2023)
- [Causal Effect Estimation: Recent Advances, Challenges, and Opportunities](https://mlsanity.com/paper/2302.00848/) (2023)
- [Deep Causal Learning: Representation, Discovery and Inference](https://mlsanity.com/paper/2211.03374/) (2022)
- [Proximity Matters: Local Proximity Enhanced Balancing for Treatment Effect Estimation](https://mlsanity.com/paper/2407.01111/) (2024)
- [Self-Distilled Disentangled Learning for Counterfactual Prediction](https://mlsanity.com/paper/2406.05855/) (2024)
- [Differentiable Pareto-Smoothed Weighting for High-Dimensional Heterogeneous Treatment Effect Estimation](https://mlsanity.com/paper/2404.17483/) (2024)
- [An Empirical Examination of Balancing Strategy for Counterfactual Estimation on Time Series](https://mlsanity.com/paper/2408.08815/) (2024)
- [On the Effects of Irrelevant Variables in Treatment Effect Estimation with Deep Disentanglement](https://mlsanity.com/paper/2407.20003/) (2024)
- [A Distributionally Robust Framework for Nuisance in Causal Effect Estimation](https://mlsanity.com/paper/2505.17717/) (2025)
- [Deep Disentangled Representation Network for Treatment Effect Estimation](https://mlsanity.com/paper/2507.06650/) (2025)
- [Recovering Latent Confounders from High-dimensional Proxy Variables](https://mlsanity.com/paper/2403.14228/) (2024)
- [Disentangled Representation via Variational AutoEncoder for Continuous Treatment Effect Estimation](https://mlsanity.com/paper/2406.02310/) (2024)
- [Disentangled Graph Autoencoder for Treatment Effect Estimation](https://mlsanity.com/paper/2412.14497/) (2024)
- [Orthogonal Uplift Learning with Permutation-Invariant Representations for Combinatorial Treatments](https://mlsanity.com/paper/2602.19851/) (2026)
- [RepFlow: Representation Enhanced Flow Matching for Causal Effect Estimation](https://mlsanity.com/paper/2605.05890/) (2026)
- [Coordinated Disentanglement with Iterative Mode Discovery Under Hidden Correlations](https://mlsanity.com/paper/2607.17264/) (2026)
- [Barycentric Fused Gromov-Wasserstein Balancing for Causal Inference under Multiple Treatments](https://mlsanity.com/paper/2608.22024/) (2026)
- [Proximal Causal Learning under Unmeasured Confounding](https://mlsanity.com/paper/2610.04519/) (2026)

## Abstract (arXiv)

Learning individual-level treatment effect is a fundamental problem in causal inference and has received increasing attention in many areas, especially in the user growth area which concerns many internet companies. Recently, disentangled representation learning methods that decompose covariates into three latent factors, including instrumental, confounding and adjustment factors, have witnessed great success in treatment effect estimation. However, it remains an open problem how to learn the underlying disentangled factors precisely. Specifically, previous methods fail to obtain independent disentangled factors, which is a necessary condition for identifying treatment effect. In this paper, we propose Disentangled Representations for Counterfactual Regression via Mutual Information Minimization (MIM-DRCFR), which uses a multi-task learning framework to share information when learning the latent factors and incorporates MI minimization learning criteria to ensure the independence of these factors. Extensive experiments including public benchmarks and real-world industrial user growth datasets demonstrate that our method performs much better than state-of-the-art methods.