Debiasing representations by removing unwanted variation due to protected attributes

Understand

We propose a regression-based approach to removing implicit biases in representations.

• On tasks where the protected attribute is observed, the method is statistically more efficient than known approaches.
• Further, we show that this approach leads to debiased representations that satisfy a first order approximation of conditional parity.
• Finally, we demonstrate the efficacy of the proposed approach by reducing racial bias in recidivism risk scores.