What's in a Name? Reducing Bias in Bios without Access to Protected Attributes

TL;DR

This paper introduces a bias mitigation method for occupation classification that uses name embeddings to reduce racial and gender biases without needing protected attribute data during deployment.

Contribution

It proposes a novel approach leveraging societal biases in word embeddings to mitigate bias without access to protected attributes, applicable at training time only.

Findings

Reduces race and gender biases effectively

Maintains high true positive rate

Works without protected attribute access during deployment

Abstract

There is a growing body of work that proposes methods for mitigating bias in machine learning systems. These methods typically rely on access to protected attributes such as race, gender, or age. However, this raises two significant challenges: (1) protected attributes may not be available or it may not be legal to use them, and (2) it is often desirable to simultaneously consider multiple protected attributes, as well as their intersections. In the context of mitigating bias in occupation classification, we propose a method for discouraging correlation between the predicted probability of an individual's true occupation and a word embedding of their name. This method leverages the societal biases that are encoded in word embeddings, eliminating the need for access to protected attributes. Crucially, it only requires access to individuals' names at training time and not at deployment time. We evaluate two variations of our proposed method using a large-scale dataset of online biographies. We find that both variations simultaneously reduce race and gender biases, with almost no reduction in the classifier's overall true positive rate.