Learning under selective labels in the presence of expert consistency

TL;DR

This paper addresses the challenge of learning from selectively labeled data in decision-making contexts, proposing a data augmentation method that leverages expert consistency to improve model reliability and fairness.

Contribution

It introduces a novel data augmentation approach that utilizes expert consistency to mitigate selective label bias and validate model reliability in selective label scenarios.

Findings

The proposed method can reduce bias caused by selective labels.

Expert consistency helps in validating the reliability of learned models.

The approach can identify potential systemic discrimination in models.

Abstract

We explore the problem of learning under selective labels in the context of algorithm-assisted decision making. Selective labels is a pervasive selection bias problem that arises when historical decision making blinds us to the true outcome for certain instances. Examples of this are common in many applications, ranging from predicting recidivism using pre-trial release data to diagnosing patients. In this paper we discuss why selective labels often cannot be effectively tackled by standard methods for adjusting for sample selection bias, even if there are no unobservables. We propose a data augmentation approach that can be used to either leverage expert consistency to mitigate the partial blindness that results from selective labels, or to empirically validate whether learning under such framework may lead to unreliable models prone to systemic discrimination.