Causal Reasoning for Algorithmic Fairness

TL;DR

This paper emphasizes the importance of causal reasoning in developing fair algorithms, reviewing existing fairness methods, and analyzing recent causality-based approaches to ensure equitable decision-making.

Contribution

It provides a comprehensive review of causality-based fairness approaches and argues for causality as essential for achieving algorithmic fairness.

Findings

Causality is crucial for understanding and ensuring fairness in algorithms.

Recent causality-based fairness methods offer promising solutions.

A detailed analysis of current approaches highlights their strengths and limitations.

Abstract

In this work, we argue for the importance of causal reasoning in creating fair algorithms for decision making. We give a review of existing approaches to fairness, describe work in causality necessary for the understanding of causal approaches, argue why causality is necessary for any approach that wishes to be fair, and give a detailed analysis of the many recent approaches to causality-based fairness.