Richard Zemel
We propose a learning algorithm for fair classification that achieves both group fairness (the proportion of members in a protected group receiving positive classification is identical to the proportion in the population as a whole), and individual fairness (similar individuals should be treated similarly). We formulate fairness as an optimization problem of finding a good representation of the data with two competing goals: to encode the data as well as possible, while simultaneously obfuscating any information about membership in the protected group. I will present some alternative formulations for the two main components of this framework, the measure of fairness, and the form of the learned representation. I will show empirical comparisons of these with earlier formulations on two datasets.