3 papers
cs.LG2019
Learning Fair Representations for Kernel Models
Zilong Tan, Samuel Yeom, Matt Fredrikson +1
Fair representations are a powerful tool for establishing criteria like statistical parity, proxy non-discrimination, and equality of opportunity in learned models. Existing techni…
cs.LG2019
FlipTest: Fairness Testing via Optimal Transport
Emily Black, Samuel Yeom, Matt Fredrikson
We present FlipTest, a black-box technique for uncovering discrimination in classifiers. FlipTest is motivated by the intuitive question: had an individual been of a different prot…
cs.LG2018
Hunting for Discriminatory Proxies in Linear Regression Models
Samuel Yeom, Anupam Datta, Matt Fredrikson
A machine learning model may exhibit discrimination when used to make decisions involving people. One potential cause for such outcomes is that the model uses a statistical proxy f…