Information-Theoretic Fairness with A Bounded Statistical Parity Constraint

TL;DR

This paper develops an information-theoretic framework for designing fair data representations that balance utility, privacy, and fairness constraints using advanced lemmas and bounds.

Contribution

It introduces new bounds and methods for creating fair representations with bounded statistical parity and privacy leakage, improving upon existing results.

Findings

Tighter bounds for fair representation design using functional representation lemmas.

Allowing some leakage improves utility in fair data representations.

Comparison of bounds through numerical examples.

Abstract

In this paper, we study an information-theoretic problem of designing a fair representation that attains bounded statistical (demographic) parity. More specifically, an agent uses some useful data $X$ to solve a task $T$. Since both $X$ and $T$ are correlated with some sensitive attribute or secret $S$, the agent designs a representation $Y$ that satisfies a bounded statistical parity and/or privacy leakage constraint, that is, such that $I(Y;S) \leq \epsilon$. Here, we relax the perfect demographic (statistical) parity and consider a bounded-parity constraint. In this work, we design the representation $Y$ that maximizes the mutual information $I(Y;T)$ about the task while satisfying a bounded compression (or encoding rate) constraint, that is, ensuring that $I(Y;X) \leq r$. Simultaneously, $Y$ satisfies the bounded statistical parity constraint $I(Y;S) \leq \epsilon$. To design $Y$, we use extended versions of the Functional Representation Lemma and the Strong Functional Representation Lemma which are based on randomization techniques and study the tightness of the obtained bounds in special cases. The main idea to derive the lower bounds is to use randomization over useful data $X$ or sensitive data $S$. Considering perfect demographic parity, i.e., $\epsilon=0$, we improve the existing results (lower bounds) by using a tighter version of the Strong Functional Representation Lemma and propose new upper bounds. We then propose upper and lower bounds for the main problem and show that allowing non-zero leakage can improve the attained utility. Finally, we study the bounds and compare them in a numerical example. The problem studied in this paper can also be interpreted as one of code design with bounded leakage and bounded rate privacy considering the sensitive attribute as a secret.