Explicit unfairness mitigation
As discussed in the previous section, explicit unfairness mitigation is achieved by adding regularizers or by including constraints within the loss function. In this section, we will expand on the explicit unfairness mitigation techniques and explore some of the recently proposed strategies for this.
Fairness constraints for a classification task
Let us first build an understanding of classification tasks in ML. Consider Y, X, and S to be random variables, corresponding to the class/label, non-sensitive input features, and sensitive input features, respectively. Our training dataset, D, will then consist of instances of these random variables:
D = { (y, x, s) }
The aim of the classification task is to find a model, M, defined by parameters, Θ, such that it is able to correctly predict the conditional probability of a class when sensitive and non-sensitive features are given, M[Y|X,S; Θ]. The model parameters are estimated by using...