A method to reduce algorithmic bias in neural-network classifiers by regularizing with the Wasserstein-2 distance between score distributions of two groups, with approximate gradients that fit into SGD.
A survey of bias in Machine Learning through the prism of Statistical Parity for the Adult Data Set
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Applications based on Machine Learning models have now become an indispensable part of the everyday life and the professional world. A critical question then recently arised among the population: Do algorithmic decisions convey any type of discrimination against specific groups of population or minorities? In this paper, we show the importance of understanding how a bias can be introduced into automatic decisions. We first present a mathematical framework for the fair learning problem, specifically in the binary classification setting. We then propose to quantify the presence of bias by using the standard Disparate Impact index on the real and well-known Adult income data set. Finally, we check the performance of different approaches aiming to reduce the bias in binary classification outcomes. Importantly, we show that some intuitive methods are ineffective. This sheds light on the fact trying to make fair machine learning models may be a particularly challenging task, in particular when the training observations contain a bias.
fields
stat.ML 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Tackling Algorithmic Bias in Neural-Network Classifiers using Wasserstein-2 Regularization
A method to reduce algorithmic bias in neural-network classifiers by regularizing with the Wasserstein-2 distance between score distributions of two groups, with approximate gradients that fit into SGD.