The Impossibility Theorem of Machine Fairness -- A Causal Perspective
This addresses the ambiguity in fairness definitions for AI systems used in social and economic settings, which is an incremental contribution to the field.
The paper tackles the problem of defining machine fairness by presenting a causal perspective on the impossibility theorem, which states that three prominent fairness metrics cannot be simultaneously satisfied, and proposes a causal goal for fairness.
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.