A Novel Regularization Approach to Fair ML
This addresses the need for simpler and more generalizable fair ML methods, though it appears incremental as it builds on existing regularization approaches.
The paper tackles the problem of fair machine learning by introducing Explicitly Deweighted Features (EDF), a simple and broadly applicable regularization method that reduces the impact of features linked to sensitive variables, allowing users to tune the trade-off between utility and fairness.
A number of methods have been introduced for the fair ML issue, most of them complex and many of them very specific to the underlying ML moethodology. Here we introduce a new approach that is simple, easily explained, and potentially applicable to a number of standard ML algorithms. Explicitly Deweighted Features (EDF) reduces the impact of each feature among the proxies of sensitive variables, allowing a different amount of deweighting applied to each such feature. The user specifies the deweighting hyperparameters, to achieve a given point in the Utility/Fairness tradeoff spectrum. We also introduce a new, simple criterion for evaluating the degree of protection afforded by any fair ML method.