Intermediate · Research
Individual fairness
Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.
TL;DR. A fairness principle stating that similar individuals should be treated similarly by a machine learning model.
Technical Definition
A fairness principle stating that similar individuals should be treated similarly by a machine learning model.
How it works
Individual fairness is a fairness metric that focuses on ensuring that comparable individuals receive comparable outcomes from an ML system. The core challenge lies in defining what constitutes 'similarity' between individuals, as an incomplete or biased similarity metric can itself lead to fairness issues. For example, treating two students with identical academic records identically in admissions reflects individual fairness.
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.