Skip to yearly menu bar Skip to main content


Fairness-Aware Learning for Continuous Attributes and Treatments

Jeremie Mary · ClĂ©ment Calauzènes · Noureddine El Karoui

Pacific Ballroom #127

Keywords: [ Fairness ]

Abstract: We address the problem of algorithmic fairness: ensuring that the outcome of a classifier is not biased towards certain values of sensitive variables such as age, race or gender. As common fairness metrics can be expressed as measures of (conditional) independence between variables, we propose to use the R\'enyi maximum correlation coefficient to generalize fairness measurement to continuous variables. We exploit Witsenhausen's characterization of the R\'enyi correlation coefficient to propose a differentiable implementation linked to $f$-divergences. This allows us to generalize fairness-aware learning to continuous variables by using a penalty that upper bounds this coefficient. Theses allows fairness to be extented to variables such as mixed ethnic groups or financial status without thresholds effects. This penalty can be estimated on mini-batches allowing to use deep nets. Experiments show favorable comparisons to state of the art on binary variables and prove the ability to protect continuous ones

Live content is unavailable. Log in and register to view live content