Mina Samizadeh

Equal opportunity is added according to the definition in "Mitigating Unwanted Biases with Adversarial Learning". Also, we are able to save and restore trained model in this implementation Signed-off-by: Mina...

"equal_opportunity" fairness notion is added as described in the "Mitigating Unwanted Biases with Adversarial Learning" paper. In this case, the adversary is only trained on positive (label=1) data points. Also,...