A Variational Approach to Privacy and Fairness

TL;DR

This paper introduces a variational framework for learning data representations that balance privacy, fairness, and utility, using Lagrangian optimization to control information sharing.

Contribution

It presents a novel variational method based on Lagrangians for simultaneously addressing privacy and fairness in data representations, compatible with existing models.

Findings

Framework effectively balances privacy and utility.

Method unifies privacy and fairness optimization.

Compatible with popular representation learning algorithms.

Abstract

In this article, we propose a new variational approach to learn private and/or fair representations. This approach is based on the Lagrangians of a new formulation of the privacy and fairness optimization problems that we propose. In this formulation, we aim to generate representations of the data that keep a prescribed level of the relevant information that is not shared by the private or sensitive data, while minimizing the remaining information they keep. The proposed approach (i) exhibits the similarities of the privacy and fairness problems, (ii) allows us to control the trade-off between utility and privacy or fairness through the Lagrange multiplier parameter, and (iii) can be comfortably incorporated to common representation learning algorithms such as the VAE, the $\beta$-VAE, the VIB, or the nonlinear IB.