# Gradient Reversal Against Discrimination

arXiv: https://arxiv.org/abs/1807.00392 · HTML: https://mlsanity.com/paper/1807.00392/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2018.

## Built on by (most cited first, 20 of 20)

- [Bias Mitigation for Machine Learning Classifiers: A Comprehensive Survey](https://mlsanity.com/paper/2207.07068/) (2022)
- [Fair Contrastive Learning for Facial Attribute Classification](https://mlsanity.com/paper/2203.16209/) (2022)
- [Efficient fair PCA for fair representation learning](https://mlsanity.com/paper/2302.13319/) (2023)
- [Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media](https://mlsanity.com/paper/2210.07518/) (2022)
- [Representation Learning and Identity Adversarial Training for Facial Behavior Understanding](https://mlsanity.com/paper/2407.11243/) (2024)
- [Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks](https://mlsanity.com/paper/2204.04440/) (2022)
- [FairGrad: Fairness Aware Gradient Descent](https://mlsanity.com/paper/2206.10923/) (2022)
- [A Realism Metric for Generated LiDAR Point Clouds](https://mlsanity.com/paper/2208.14958/) (2022)
- [Can Large Language Models (or Humans) Disentangle Text?](https://mlsanity.com/paper/2403.16584/) (2024)
- [Quantifying point cloud realism through adversarially learned latent representations](https://mlsanity.com/paper/2109.11775/) (2021)
- [Benign Shortcut for Debiasing: Fair Visual Recognition via Intervention with Shortcut Features](https://mlsanity.com/paper/2308.08482/) (2023)
- [A Self-Supervised Learning Pipeline for Demographically Fair Facial Attribute Classification](https://mlsanity.com/paper/2407.10104/) (2024)
- [Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation](https://mlsanity.com/paper/2507.20284/) (2025)
- [Mitigating Urban-Rural Disparities in Contrastive Representation Learning with Satellite Imagery](https://mlsanity.com/paper/2211.08672/) (2022)
- [SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognition](https://mlsanity.com/paper/2602.05162/) (2026)
- [Fair Visual Recognition via Intervention with Proxy Features](https://mlsanity.com/paper/2211.01253/) (2022)
- [What Happens to a Dataset Transformed by a Projection-based Concept Removal Method?](https://mlsanity.com/paper/2403.16142/) (2024)
- [Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2508.18886/) (2025)
- [ProtoFair: Fair Self-Supervised Contrastive Learning via Pseudo-Counterfactual Pairs](https://mlsanity.com/paper/2605.01971/) (2026)
- [Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization](https://mlsanity.com/paper/2608.22820/) (2026)

## Abstract (arXiv)

No methods currently exist for making arbitrary neural networks fair. In this work we introduce GRAD, a new and simplified method to producing fair neural networks that can be used for auto-encoding fair representations or directly with predictive networks. It is easy to implement and add to existing architectures, has only one (insensitive) hyper-parameter, and provides improved individual and group fairness. We use the flexibility of GRAD to demonstrate multi-attribute protection.