Using Wasserstein-2 regularization to ensure fair decisions with Neural-Network classifiers

08/15/2019
by   Laurent Risser, et al.
0

In this paper, we propose a new method to build fair Neural-Network classifiers by using a constraint based on the Wasserstein distance. More specifically, we detail how to efficiently compute the gradients of Wasserstein-2 regularizers for Neural-Networks. The proposed strategy is then used to train Neural-Networks decision rules which favor fair predictions. Our method fully takes into account two specificities of Neural-Networks training: (1) The network parameters are indirectly learned based on automatic differentiation and on the loss gradients, and (2) batch training is the gold standard to approximate the parameter gradients, as it requires a reasonable amount of computations and it can efficiently explore the parameters space. Results are shown on synthetic data, as well as on the UCI Adult Income Dataset. Our method is shown to perform well compared with 'ZafarICWWW17' and linear-regression with Wasserstein-1 regularization, as in 'JiangUAI19', in particular when non-linear decision rules are required for accurate predictions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/12/2022

On Generalization and Regularization via Wasserstein Distributionally Robust Optimization

Wasserstein distributionally robust optimization (DRO) has found success...
research
10/28/2019

Approximate Bayesian Computation with the Sliced-Wasserstein Distance

Approximate Bayesian Computation (ABC) is a popular method for approxima...
research
01/28/2022

Wasserstein Iterative Networks for Barycenter Estimation

Wasserstein barycenters have become popular due to their ability to repr...
research
06/17/2015

Learning with a Wasserstein Loss

Learning to predict multi-label outputs is challenging, but in many prob...
research
01/24/2019

Pretending Fair Decisions via Stealthily Biased Sampling

Fairness by decision-makers is believed to be auditable by third parties...
research
08/07/2017

Wasserstein Dictionary Learning: Optimal Transport-based unsupervised non-linear dictionary learning

This article introduces a new non-linear dictionary learning method for ...
research
02/13/2020

Regularizing activations in neural networks via distribution matching with the Wasserstein metric

Regularization and normalization have become indispensable components in...

Please sign up or login with your details

Forgot password? Click here to reset