Existing classification models often output discriminatory results since they learn the target
attribute without addressing data imbalance with respect to the protected attributes (eg …

In machine learning (ML) applications, unfair predictions may discriminate against a minority
group. Most existing approaches for fair machine learning (FML) treat fairness as a …

© 2020 for this paper by its authors. Increasing concern about discrimination and bias in
datadriven decision making systems has led to a growth in academic and popular interest in …

Algorithmic Fairness is an established area of machine learning, willing to reduce the
influence of hidden bias in the data. Yet, despite its wide range of applications, very few …

Disparate treatment occurs when a machine learning model produces different decisions for
groups of individuals based on a sensitive attribute (eg, age, sex). In domains where …

In real-world classification settings, such as loan application evaluation or content
moderation on online platforms, individuals respond to classifier predictions by strategically …

Fair classification and fair representation learning are two important problems in supervised
and unsupervised fair machine learning, respectively. Fair classification asks for a classifier …

In this work we formulate and formally characterize group fairness as a multi-objective
optimization problem, where each sensitive group risk is a separate objective. We propose a …

Machine learning models are trained to minimize the mean loss for a single metric, and thus
typically do not consider fairness and robustness. Neglecting such metrics in training can …

Common fairness definitions in machine learning focus on balancing notions of disparity
and utility. In this work, we study fairness in the context of risk disparity among sub …