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.
Fairness Violations and Mitigation under Distribution Shift
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
Introduction
Motivation
Method
Solution
Summary
Taught by
ACM FAccT Conference
Related Courses
-
Fairness Through Robustness - Investigating Robustness Disparity in Deep Learning
-
Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information
-
Can You Fake It Until You Make It? - Impacts of Differentially Private Synthetic Data on Downstream Classification Fairness
-
Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
