The Impossibility Theorem of Machine Fairness -- A Causal Perspective

TL;DR

This paper presents a causal perspective on the impossibility of satisfying all fairness metrics simultaneously in machine learning, highlighting the ambiguity in defining fairness.

Contribution

It introduces a causal framework for understanding the impossibility theorem of machine fairness and proposes a causal goal for fairness.

Findings

Statistically, all three prominent fairness metrics cannot be satisfied simultaneously.

A causal perspective clarifies the inherent trade-offs in fairness definitions.

Proposes a causal goal to guide fair machine learning practices.

Abstract

With the increasing pervasive use of machine learning in social and economic settings, there has been an interest in the notion of machine bias in the AI community. Models trained on historic data reflect biases that exist in society and propagated them to the future through their decisions. There are three prominent metrics of machine fairness used in the community, and it has been shown statistically that it is impossible to satisfy them all at the same time. This has led to an ambiguity with regards to the definition of fairness. In this report, a causal perspective to the impossibility theorem of fairness is presented along with a causal goal for machine fairness.