Timezone: »

 
Poster
Fair Learning with Private Demographic Data
Hussein Mozannar · Mesrob Ohannessian · Nati Srebro

Tue Jul 14 07:00 AM -- 07:45 AM & Tue Jul 14 06:00 PM -- 06:45 PM (PDT) @ Virtual
in Poster Session 1 »

Sensitive attributes such as race are rarely available to learners in real world settings as their collection is often restricted by laws and regulations. We give a scheme that allows individuals to release their sensitive information privately while still allowing any downstream entity to learn non-discriminatory predictors. We show how to adapt non-discriminatory learners to work with privatized protected attributes giving theoretical guarantees on performance. Finally, we highlight how the methodology could apply to learning fair predictors in settings where protected attributes are only available for a subset of the data.

Keywords: Privacy-preserving Statistics and Machine Learning · Fairness, Equity and Justice · Fairness, Equity, Justice, and Safety
[ Slides] 

Author Information

Hussein Mozannar (Massachusetts Institute of Technology)
Mesrob Ohannessian (University of Illinois at Chicago)
Nati Srebro (Toyota Technological Institute at Chicago)

More from the Same Authors