fairret: a Framework for Differentiable Fairness Regularization Terms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Buyl, Maarten, Defrance, MaryBeth, De Bie, Tijl
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916198967410688
author Buyl, Maarten
Defrance, MaryBeth
De Bie, Tijl
author_facet Buyl, Maarten
Defrance, MaryBeth
De Bie, Tijl
contents Current fairness toolkits in machine learning only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play in modern machine learning pipelines. We introduce a framework of fairness regularization terms (fairrets) which quantify bias as modular, flexible objectives that are easily integrated in automatic differentiation pipelines. By employing a general definition of fairness in terms of linear-fractional statistics, a wide class of fairrets can be computed efficiently. Experiments show the behavior of their gradients and their utility in enforcing fairness with minimal loss of predictive power compared to baselines. Our contribution includes a PyTorch implementation of the fairret framework.
format Preprint
id arxiv_https___arxiv_org_abs_2310_17256
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle fairret: a Framework for Differentiable Fairness Regularization Terms
Buyl, Maarten
Defrance, MaryBeth
De Bie, Tijl
Machine Learning
Current fairness toolkits in machine learning only admit a limited range of fairness definitions and have seen little integration with automatic differentiation libraries, despite the central role these libraries play in modern machine learning pipelines. We introduce a framework of fairness regularization terms (fairrets) which quantify bias as modular, flexible objectives that are easily integrated in automatic differentiation pipelines. By employing a general definition of fairness in terms of linear-fractional statistics, a wide class of fairrets can be computed efficiently. Experiments show the behavior of their gradients and their utility in enforcing fairness with minimal loss of predictive power compared to baselines. Our contribution includes a PyTorch implementation of the fairret framework.
title fairret: a Framework for Differentiable Fairness Regularization Terms
topic Machine Learning
url https://arxiv.org/abs/2310.17256