Metric-Fair Classifier Derandomization

TL;DR

This paper explores how to convert stochastic classifiers into deterministic ones while maintaining metric fairness, balancing output accuracy and fairness guarantees through novel derandomization techniques.

Contribution

It introduces a new derandomization method that offers a tradeoff between fairness and approximation, improving upon prior approaches in metric fairness preservation.

Findings

Prior derandomization is nearly maximally unfair.

Simple random threshold achieves optimal fairness but weaker approximation.

Proposed method balances fairness and accuracy effectively.

Abstract

We study the problem of classifier derandomization in machine learning: given a stochastic binary classifier $f: X \to [0,1]$, sample a deterministic classifier $\hat{f}: X \to \{0,1\}$ that approximates the output of $f$ in aggregate over any data distribution. Recent work revealed how to efficiently derandomize a stochastic classifier with strong output approximation guarantees, but at the cost of individual fairness -- that is, if $f$ treated similar inputs similarly, $\hat{f}$ did not. In this paper, we initiate a systematic study of classifier derandomization with metric fairness guarantees. We show that the prior derandomization approach is almost maximally metric-unfair, and that a simple ``random threshold'' derandomization achieves optimal fairness preservation but with weaker output approximation. We then devise a derandomization procedure that provides an appealing tradeoff between these two: if $f$ is $\alpha$-metric fair according to a metric $d$ with a locality-sensitive hash (LSH) family, then our derandomized $\hat{f}$ is, with high probability, $O(\alpha)$-metric fair and a close approximation of $f$. We also prove generic results applicable to all (fair and unfair) classifier derandomization procedures, including a bias-variance decomposition and reductions between various notions of metric fairness.