Adversarial Learned Fair Representations using Dampening and Stacking
This addresses fairness in machine learning for automated decision-making, but it is incremental as it builds upon existing adversarial learning methods.
The paper tackled the problem of learning fair representations to censor sensitive variables in automated decisions, introducing a novel algorithm using dampening and stacking that improved upon earlier work in both censoring and reconstruction.
As more decisions in our daily life become automated, the need to have machine learning algorithms that make fair decisions increases. In fair representation learning we are tasked with finding a suitable representation of the data in which a sensitive variable is censored. Recent work aims to learn fair representations through adversarial learning. This paper builds upon this work by introducing a novel algorithm which uses dampening and stacking to learn adversarial fair representations. Results show that that our algorithm improves upon earlier work in both censoring and reconstruction.