# Causality-aware counterfactual confounding adjustment for feature representations learned by deep models

arXiv: https://arxiv.org/abs/2004.09466 · HTML: https://mlsanity.com/paper/2004.09466/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2020.

## Built on by (most cited first, 2 of 2)

- [Finding and Fixing Spurious Patterns with Explanations](https://mlsanity.com/paper/2106.02112/) (2021)
- [Matched sample selection with GANs for mitigating attribute confounding](https://mlsanity.com/paper/2103.13455/) (2021)

## Abstract (arXiv)

Causal modeling has been recognized as a potential solution to many challenging problems in machine learning (ML). Here, we describe how a recently proposed counterfactual approach developed to deconfound linear structural causal models can still be used to deconfound the feature representations learned by deep neural network (DNN) models. The key insight is that by training an accurate DNN using softmax activation at the classification layer, and then adopting the representation learned by the last layer prior to the output layer as our features, we have that, by construction, the learned features will fit well a (multi-class) logistic regression model, and will be linearly associated with the labels. As a consequence, deconfounding approaches based on simple linear models can be used to deconfound the feature representations learned by DNNs. We validate the proposed methodology using colored versions of the MNIST dataset. Our results illustrate how the approach can effectively combat confounding and improve model stability in the context of dataset shifts generated by selection biases.