Explore cutting-edge research on fairness in machine learning algorithms in this 46-minute conference session from FAT* 2019. Delve into three presentations addressing crucial topics in algorithmic fairness: assessing disparity when protected class information is unobserved, a meta-algorithm for classification with fairness constraints, and a comparative study of fairness-enhancing interventions. Chaired by Nicole Immorlica, this session features talks by researchers from various institutions, offering insights into the challenges and potential solutions for creating more equitable machine learning systems. Gain a deeper understanding of the intersection between fairness, accountability, and transparency in AI and machine learning through these thought-provoking discussions.
Overview
Syllabus
Zhao Gao
Classification Problem
Personal Note
Thomas
Math
Data
Interventions
Fairness
Thank you
Questions
Taught by
ACM FAccT Conference
Related Courses
-
Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information
-
Probing ML Models for Fairness with the What-if Tool and SHAP
-
Framing and Abstraction
-
Fairness Through Robustness - Investigating Robustness Disparity in Deep Learning
-
Bridging Machine Learning and Mechanism Design towards Algorithmic Fairness
-
Toward a Theory of Race for Fairness in Machine Learning
