DeepAI AI Chat
Log In Sign Up

Fair NLP Models with Differentially Private Text Encoders

by   Gaurav Maheshwari, et al.

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.


page 1

page 2

page 3

page 4


When differential privacy meets NLP: The devil is in the detail

Differential privacy provides a formal approach to privacy of individual...

A Variational Approach to Privacy and Fairness

In this article, we propose a new variational approach to learn private ...

Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach

A critical concern in data-driven decision making is to build models who...

Towards Robust and Privacy-preserving Text Representations

Written text often provides sufficient clues to identify the author, the...

Improving Fairness and Privacy in Selection Problems

Supervised learning models have been increasingly used for making decisi...

Stochastic Differentially Private and Fair Learning

Machine learning models are increasingly used in high-stakes decision-ma...

Overlearning Reveals Sensitive Attributes

`Overlearning' means that a model trained for a seemingly simple objecti...