Group Fairness - Independence Revisited
Offered By: Association for Computing Machinery (ACM) via YouTube
Course Description
Overview
Explore the concept of group fairness and independence in this 17-minute conference talk from the FAccT 2021 virtual event. Delve into the research presented by T. Räz, examining the intricacies of fairness in machine learning and algorithmic decision-making. Learn about key definitions, the challenges of gerrymandering, and the insufficiency of separation as a fairness metric. Investigate why independence can be considered unfair and how increments of accuracy impact fairness assessments. Gain valuable insights into the complexities of fairness in AI systems and the ongoing research in this critical field.
Syllabus
Introduction
Background
Definitions
gerrymandering
separation insufficiency
independence is unfair
increments of accuracy
conclusions
Taught by
ACM FAccT Conference
Related Courses
Can Algorithms Bend the Arc Toward Justice?Santa Fe Institute via YouTube Measurement and Fairness
Association for Computing Machinery (ACM) via YouTube Removing Spurious Features Can Hurt Accuracy and Affect Groups Disproportionately
Association for Computing Machinery (ACM) via YouTube Chasing Your Long Tails - Differentially Private Prediction in Health Care Settings
Association for Computing Machinery (ACM) via YouTube One Label, One Billion Faces - Usage and Consistency of Racial Categories in Computer Vision
Association for Computing Machinery (ACM) via YouTube