Predict Responsibly: Improving Fairness and Accuracy by Learning to Defer

TL;DR

This paper introduces a 'learning to defer' framework that improves fairness and accuracy in decision systems by optimally choosing when to pass decisions to external agents, accounting for their biases.

Contribution

It generalizes rejection learning by modeling interactions with external decision-makers, enhancing system fairness and accuracy even with biased or inconsistent agents.

Findings

Learning to defer improves overall system accuracy.

The approach reduces bias in decision-making systems.

Deferment strategies outperform rejection learning in biased settings.

Abstract

In many machine learning applications, there are multiple decision-makers involved, both automated and human. The interaction between these agents often goes unaddressed in algorithmic development. In this work, we explore a simple version of this interaction with a two-stage framework containing an automated model and an external decision-maker. The model can choose to say "Pass", and pass the decision downstream, as explored in rejection learning. We extend this concept by proposing "learning to defer", which generalizes rejection learning by considering the effect of other agents in the decision-making process. We propose a learning algorithm which accounts for potential biases held by external decision-makers in a system. Experiments demonstrate that learning to defer can make systems not only more accurate but also less biased. Even when working with inconsistent or biased users, we show that deferring models still greatly improve the accuracy and/or fairness of the entire system.