# Debiasing Convolutional Neural Networks via Meta Orthogonalization

arXiv: https://arxiv.org/abs/2011.07453 · HTML: https://mlsanity.com/paper/2011.07453/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2020.

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

- [Post-hoc Orthogonalization for Mitigation of Protected Feature Bias in CXR Embeddings](https://mlsanity.com/paper/2311.01349/) (2023)

## Abstract (arXiv)

While deep learning models often achieve strong task performance, their successes are hampered by their inability to disentangle spurious correlations from causative factors, such as when they use protected attributes (e.g., race, gender, etc.) to make decisions. In this work, we tackle the problem of debiasing convolutional neural networks (CNNs) in such instances. Building off of existing work on debiasing word embeddings and model interpretability, our Meta Orthogonalization method encourages the CNN representations of different concepts (e.g., gender and class labels) to be orthogonal to one another in activation space while maintaining strong downstream task performance. Through a variety of experiments, we systematically test our method and demonstrate that it significantly mitigates model bias and is competitive against current adversarial debiasing methods.