# Tackling Algorithmic Bias in Neural-Network Classifiers using Wasserstein-2 Regularization

arXiv: https://arxiv.org/abs/1908.05783 · HTML: https://mlsanity.com/paper/1908.05783/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2019.

## Built on by (most cited first, 18 of 18)

- [Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers](https://mlsanity.com/paper/2203.04913/) (2022)
- [Transport-based Counterfactual Models](https://mlsanity.com/paper/2108.13025/) (2021)
- [An improved central limit theorem and fast convergence rates for entropic transportation costs](https://mlsanity.com/paper/2204.09105/) (2022)
- [Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks](https://mlsanity.com/paper/2204.04440/) (2022)
- [Group-blind optimal transport to group parity and its constrained variants](https://mlsanity.com/paper/2310.11407/) (2023)
- [Fair Text Classification with Wasserstein Independence](https://mlsanity.com/paper/2311.12689/) (2023)
- [Fairness-Aware Grouping for Continuous Sensitive Variables: Application for Debiasing Face Analysis with respect to Skin Tone](https://mlsanity.com/paper/2507.11247/) (2025)
- [A survey of Identification and mitigation of Machine Learning algorithmic biases in Image Analysis](https://mlsanity.com/paper/2210.04491/) (2022)
- [Fair Text Classification via Transferable Representations](https://mlsanity.com/paper/2503.07691/) (2025)
- [How optimal transport can tackle gender biases in multi-class neural-network classifiers for job recommendations?](https://mlsanity.com/paper/2302.14063/) (2023)
- [Learning with Differentially Private (Sliced) Wasserstein Gradients](https://mlsanity.com/paper/2502.01701/) (2025)
- [Linking convolutional kernel size to generalization bias in face analysis CNNs](https://mlsanity.com/paper/2302.03750/) (2023)
- [Debiasing Machine Learning Models by Using Weakly Supervised Learning](https://mlsanity.com/paper/2402.15477/) (2024)
- [On the Nonconvexity of Push-Forward Constraints and Its Consequences in Machine Learning](https://mlsanity.com/paper/2403.07471/) (2024)
- [Fair Graph Neural Network with Supervised Contrastive Regularization](https://mlsanity.com/paper/2404.06090/) (2024)
- [PLS-based approach for fair representation learning](https://mlsanity.com/paper/2502.16263/) (2025)
- [Model-Agnostic Fairness Regularization for GNNs with Incomplete Sensitive Information](https://mlsanity.com/paper/2512.03074/) (2025)
- [Convergence of empirical subgradients for optimal transport-based objectives](https://mlsanity.com/paper/2605.28134/) (2026)

## Abstract (arXiv)

The increasingly common use of neural network classifiers in industrial and social applications of image analysis has allowed impressive progress these last years. Such methods are however sensitive to algorithmic bias, i.e. to an under- or an over-representation of positive predictions or to higher prediction errors in specific subgroups of images. We then introduce in this paper a new method to temper the algorithmic bias in Neural-Network based classifiers. Our method is Neural-Network architecture agnostic and scales well to massive training sets of images. It indeed only overloads the loss function with a Wasserstein-2 based regularization term for which we back-propagate the impact of specific output predictions using a new model, based on the Gateaux derivatives of the predictions distribution. This model is algorithmically reasonable and makes it possible to use our regularized loss with standard stochastic gradient-descent strategies. Its good behavior is assessed on the reference Adult census, MNIST, CelebA datasets.