The Frontiers of Fairness in Machine Learning

TL;DR

This paper reviews the current state and future directions of fairness in machine learning, highlighting the nascent scientific understanding and recent theoretical advances in the field.

Contribution

It provides a comprehensive survey of recent theoretical work and identifies promising research directions in the emerging science of fairness in machine learning.

Findings

The field of fairness in machine learning is still in early development.

Recent theoretical work offers new insights into fairness metrics and algorithms.

The report outlines promising future research directions.

Abstract

The last few years have seen an explosion of academic and popular interest in algorithmic fairness. Despite this interest and the volume and velocity of work that has been produced recently, the fundamental science of fairness in machine learning is still in a nascent state. In March 2018, we convened a group of experts as part of a CCC visioning workshop to assess the state of the field, and distill the most promising research directions going forward. This report summarizes the findings of that workshop. Along the way, it surveys recent theoretical work in the field and points towards promising directions for research.