Fair NLP Models with Differentially Private Text Encoders - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year :

Fair NLP Models with Differentially Private Text Encoders

Abstract

Encoded text representations often capture sensitive attributes about individuals (e.g., race or gender), which raise privacy concerns and can make downstream models unfair to certain groups. In this work, we propose FEDERATE, an approach that combines ideas from differential privacy and adversarial training to learn private text representations which also induces fairer models. We empirically evaluate the trade-off between the privacy of the representations and the fairness and accuracy of the downstream model on four NLP datasets. Our results show that FEDERATE consistently improves upon previous methods, and thus suggest that privacy and fairness can positively reinforce each other.
Fichier principal
Vignette du fichier
2205.06135.pdf (700.05 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03905094 , version 1 (17-12-2022)

Identifiers

Cite

Gaurav Maheshwari, Pascal Denis, Mikaela Keller, Aurélien Bellet. Fair NLP Models with Differentially Private Text Encoders. Findings of the Association for Computational Linguistics: EMNLP 2022, 2022, Abu Dhabi, United Arab Emirates. ⟨hal-03905094⟩
12 View
4 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More