AI Chat AI Image Generator AI Video Text to Speech

Gradient Reversal Against Discrimination

07/01/2018

∙

by Edward Raff, et al.

∙

∙

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.

Edward Raff
74 publications
Jared Sylvester
8 publications

page 1

page 2

page 3

page 4

research

∙ 05/28/2018

FairGAN: Fairness-aware Generative Adversarial Networks

Fairness-aware learning is increasingly important in data mining. Discri...

0 Depeng Xu, et al. ∙

research

∙ 04/21/2023

Individual Fairness in Bayesian Neural Networks

We study Individual Fairness (IF) for Bayesian neural networks (BNNs). S...

0 Alice Doherty, et al. ∙

research

∙ 02/21/2020

Learning Fairness-aware Relational Structures

The development of fair machine learning models that effectively avert b...

0 Yue Zhang, et al. ∙

research

∙ 02/15/2021

Fair and Optimal Cohort Selection for Linear Utilities

The rise of algorithmic decision-making has created an explosion of rese...

0 Konstantina Bairaktari, et al. ∙

research

∙ 12/21/2017

Fair Forests: Regularized Tree Induction to Minimize Model Bias

The potential lack of fairness in the outputs of machine learning algori...

0 Edward Raff, et al. ∙

research

∙ 08/13/2022

A Novel Regularization Approach to Fair ML

A number of methods have been introduced for the fair ML issue, most of ...

10 Norman Matloff, et al. ∙