# Variational Auto-Encoder Architectures that Excel at Causal Inference

arXiv: https://arxiv.org/abs/2111.06486 · HTML: https://mlsanity.com/paper/2111.06486/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 37 references that are in the map.
- First posted on arXiv 11 Nov 2021.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Understanding disentangling in β-VAE](https://mlsanity.com/paper/1804.03599/) (2018)
- [Learning Representations for Counterfactual Inference](https://mlsanity.com/paper/1605.03661/) (2016)
- [Adapting Neural Networks for the Estimation of Treatment Effects](https://mlsanity.com/paper/1906.02120/) (2019)
- [The Variational Fair Autoencoder](https://mlsanity.com/paper/1511.00830/) (2015)
- [Treatment effect estimation with disentangled latent factors](https://mlsanity.com/paper/2001.10652/) (2020)
- [Information Constraints on Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1805.08672/) (2018)
- [Counterfactual Propagation for Semi-Supervised Individual Treatment Effect Estimation](https://mlsanity.com/paper/2005.05099/) (2020)

## Built on by (most cited first, 1 of 1)

- [Multiple Domain Causal Networks](https://mlsanity.com/paper/2205.06791/) (2022)

## Abstract (arXiv)

Estimating causal effects from observational data (at either an individual -- or a population -- level) is critical for making many types of decisions. One approach to address this task is to learn decomposed representations of the underlying factors of data; this becomes significantly more challenging when there are confounding factors (which influence both the cause and the effect). In this paper, we take a generative approach that builds on the recent advances in Variational Auto-Encoders to simultaneously learn those underlying factors as well as the causal effects. We propose a progressive sequence of models, where each improves over the previous one, culminating in the Hybrid model. Our empirical results demonstrate that the performance of all three proposed models are superior to both state-of-the-art discriminative as well as other generative approaches in the literature.