Fairness Violations and Mitigation under Distribution Shift

Explore a conference talk that delves into the critical issue of fairness violations in machine learning models under covariate shift conditions. Examine the motivations behind this research, understand the methodologies employed, and discover proposed solutions for mitigating fairness issues when distribution shifts occur. Learn from H. Singh, R. Singh, V. Mhasawade, and R. Chunara as they present their findings at the FAccT 2021 virtual conference. Gain insights into the challenges of maintaining fairness in AI systems when faced with changing data distributions and explore practical approaches to address these concerns.

Introduction
Motivation
Method
Solution
Summary