Fair NLP Models with Differentially Private Text Encoders - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Fair NLP Models with Differentially Private Text Encoders

Résumé

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
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

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

Identifiants

Citer

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⟩
31 Consultations
19 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More