Advanced · Research
Incompatibility of fairness metrics
Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.
TL;DR. The mathematical reality that some definitions of fairness cannot be simultaneously satisfied, requiring context-specific choices.
Technical Definition
The mathematical reality that some definitions of fairness cannot be simultaneously satisfied, requiring context-specific choices.
How it works
This concept highlights that different mathematical metrics for fairness can be mutually exclusive, meaning achieving one perfectly can prevent another from being met. Consequently, there isn't a universal fairness metric applicable to all machine learning scenarios. This doesn't negate fairness efforts but emphasizes the need to define and prioritize fairness based on the specific context and potential harms of an application.
Related Concepts
- Fairness — The principle that AI systems should treat individuals and groups equitably.
- Bias (ethics/fairness) — Unfair prejudice or favoritism towards certain groups or things, which can influence data, system design, and user interactions.
- Responsible AI (RAI) — A holistic framework encompassing the ethical, legal, and societal implications of AI, promoting trustworthy and beneficial systems.