# Bridging the Generalization Gap: Training Robust Models on Confounded Biological Data

arXiv: https://arxiv.org/abs/1812.04778 · HTML: https://mlsanity.com/paper/1812.04778/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2018.

## Built on by (most cited first, 3 of 3)

- [A Penalty Approach for Normalizing Feature Distributions to Build Confounder-Free Models](https://mlsanity.com/paper/2207.04607/) (2022)
- [Adversarially-regularized mixed effects deep learning (ARMED) models for improved interpretability, performance, and generalization on clustered data](https://mlsanity.com/paper/2202.11783/) (2022)
- [Confounder-Free Continual Learning via Recursive Feature Normalization](https://mlsanity.com/paper/2507.09031/) (2025)

## Abstract (arXiv)

Statistical learning on biological data can be challenging due to confounding variables in sample collection and processing. Confounders can cause models to generalize poorly and result in inaccurate prediction performance metrics if models are not validated thoroughly. In this paper, we propose methods to control for confounding factors and further improve prediction performance. We introduce OrthoNormal basis construction In cOnfounding factor Normalization (ONION) to remove confounding covariates and use the Domain-Adversarial Neural Network (DANN) to penalize models for encoding confounder information. We apply the proposed methods to simulated and empirical patient data and show significant improvements in generalization.