Gradient Reversal Against Discrimination

2018/07/01 by Edward Raff, Raff, Edward, Jared Sylvester +1 · 3 citations
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.1807.00392

openalex publication_date 2018/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models
• Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation
• Turning a Blind Eye: Explicit Removal of Biases and Variation from Deep\n Neural Network Embeddings

Related

• FETA: Fairness Enforced Verifying, Training, and Predicting Algorithms for Neural Networks
• Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks
• FaiR-N: Fair and Robust Neural Networks for Structured Data
• FairGrad: Fairness Aware Gradient Descent
• FairQuant: Certifying and Quantifying Fairness of Deep Neural Networks