Fair Text Classification via Transferable Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Leteno, Thibaud, Perrot, Michael, Laclau, Charlotte, Gourru, Antoine, Gravier, Christophe
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908694577414144
author Leteno, Thibaud
Perrot, Michael
Laclau, Charlotte
Gourru, Antoine
Gravier, Christophe
author_facet Leteno, Thibaud
Perrot, Michael
Laclau, Charlotte
Gourru, Antoine
Gravier, Christophe
contents Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g., women and men) remains an open challenge. We propose an approach that extends the use of the Wasserstein Dependency Measure for learning unbiased neural text classifiers. Given the challenge of distinguishing fair from unfair information in a text encoder, we draw inspiration from adversarial training by inducing independence between representations learned for the target label and those for a sensitive attribute. We further show that Domain Adaptation can be efficiently leveraged to remove the need for access to the sensitive attributes in the dataset we cure. We provide both theoretical and empirical evidence that our approach is well-founded.
format Preprint
id arxiv_https___arxiv_org_abs_2503_07691
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fair Text Classification via Transferable Representations
Leteno, Thibaud
Perrot, Michael
Laclau, Charlotte
Gourru, Antoine
Gravier, Christophe
Machine Learning
Computation and Language
Group fairness is a central research topic in text classification, where reaching fair treatment between sensitive groups (e.g., women and men) remains an open challenge. We propose an approach that extends the use of the Wasserstein Dependency Measure for learning unbiased neural text classifiers. Given the challenge of distinguishing fair from unfair information in a text encoder, we draw inspiration from adversarial training by inducing independence between representations learned for the target label and those for a sensitive attribute. We further show that Domain Adaptation can be efficiently leveraged to remove the need for access to the sensitive attributes in the dataset we cure. We provide both theoretical and empirical evidence that our approach is well-founded.
title Fair Text Classification via Transferable Representations
topic Machine Learning
Computation and Language
url https://arxiv.org/abs/2503.07691