In-Training Model Bias Mitigation
Understand how to mitigate model bias during training using adversarial debiasing methods that reduce dependence on protected classes. Learn about the fairness-accuracy trade-off and how Pareto frontiers help select optimal models balancing fairness and accuracy.
We'll cover the following...
In-training methods are a much more optimal way of solving for bias but are done while the model is training and are usually computationally more expensive.
Adversarial debiasing
For synthetic data generation, adversarial methods create a digital twin of the data by using two different algorithms. One algorithm (the generator) creates potential synthetic rows and another (the discriminator) guesses whether the new rows are synthetic or real. Over time, the generator learns to generate better and better rows.
Adversarial debiasing works similarly, also using two algorithims:
Generator: Makes predictions given input variables
...