An Introduction to Algorithmic Fairness

TL;DR

This paper introduces core concepts of algorithmic fairness, discussing types of fairness-related harms, main fairness notions, and underlying biases in machine learning systems.

Contribution

It provides an accessible overview of key ideas and frameworks in algorithmic fairness research, highlighting the connection between biases and fairness issues.

Findings

Different types of fairness-related harms identified

Two main notions of algorithmic fairness explained

Biases in machine learning linked to fairness concerns

Abstract

In recent years, there has been an increasing awareness of both the public and scientific community that algorithmic systems can reproduce, amplify, or even introduce unfairness in our societies. These lecture notes provide an introduction to some of the core concepts in algorithmic fairness research. We list different types of fairness-related harms, explain two main notions of algorithmic fairness, and map the biases that underlie these harms upon the machine learning development process.