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.
Are there examples start to finish of training a model to predict an outcome and minimize prediction of a protected class, using adversarial debiasing? I have not been able to locate one, and it would be extremely helpful in figuring out how to apply the package's functions.
Are there examples start to finish of training a model to predict an outcome and minimize prediction of a protected class, using adversarial debiasing? I have not been able to locate one, and it would be extremely helpful in figuring out how to apply the package's functions.