A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
"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, you are able to save and restore the trained model in this new code.
"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, you are able to save and restore the trained model in this new code.
Signed-off-by: Mina Samizadeh mina.smz2016@gmail.com