Related papers: How Far Can Fairness Constraints Help Recover From…
In this paper, we study the prediction of a real-valued target, such as a risk score or recidivism rate, while guaranteeing a quantitative notion of fairness with respect to a protected attribute such as gender or race. We call this class…
Minimizing risk with fairness constraints is one of the popular approaches to learning a fair classifier. Recent works showed that this approach yields an unfair classifier if the training set is corrupted. In this work, we study the…
Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent trends favor algorithmic methods that embed fairness into the training process. These methods steer models towards fair…
Class imbalance in real-world data poses a common bottleneck for machine learning tasks, since achieving good generalization on under-represented examples is often challenging. Mitigation strategies, such as under or oversampling the data…
Due to the recent cases of algorithmic bias in data-driven decision-making, machine learning methods are being put under the microscope in order to understand the root cause of these biases and how to correct them. Here, we consider a basic…
Numerous algorithms have been produced for the fundamental problem of clustering under many different notions of fairness. Perhaps the most common family of notions currently studied is group fairness, in which proportional group…
Algorithmic fairness plays an increasingly critical role in machine learning research. Several group fairness notions and algorithms have been proposed. However, the fairness guarantee of existing fair classification methods mainly depends…
Recently there has been sustained interest in modifying prediction algorithms to satisfy fairness constraints. These constraints are typically complex nonlinear functionals of the observed data distribution. Focusing on the path-specific…
Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity concerns. Prediction models may discover, use, or amplify spurious correlations based on gender or other…
To ensure unbiased and ethical automated predictions, fairness must be a core principle in machine learning applications. Fairness in machine learning aims to mitigate biases present in the training data and model imperfections that could…
In Machine Learning, an accepted definition of fairness of a decision taken by a classifier is that it should not depend on protected features, such as gender. Unfortunately, when constraints exist between features, such dependencies can be…
Labeled datasets reflect the biases of their annotation pipelines, which sometimes introduce label bias: group-conditional label errors that cause systematic performance disparities across demographic subgroups. Label bias in image…
Machine Learning techniques have become pervasive across a range of different applications, and are now widely used in areas as disparate as recidivism prediction, consumer credit-risk analysis and insurance pricing. The prevalence of…
Data and algorithms have the potential to produce and perpetuate discrimination and disparate treatment. As such, significant effort has been invested in developing approaches to defining, detecting, and eliminating unfair outcomes in…
Data-driven software is increasingly being used as a critical component of automated decision-support systems. Since this class of software learns its logic from historical data, it can encode or amplify discriminatory practices. Previous…
Fairness is an increasingly important factor in re-ranking tasks. Prior work has identified a trade-off between ranking accuracy and item fairness. However, the underlying mechanisms are still not fully understood. An analogy can be drawn…
Consequential decisions are increasingly informed by sophisticated data-driven predictive models. However, to consistently learn accurate predictive models, one needs access to ground truth labels. Unfortunately, in practice, labels may…
We consider the weakly supervised binary classification problem where the labels are randomly flipped with probability $1- {\alpha}$. Although there exist numerous algorithms for this problem, it remains theoretically unexplored how the…
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 works consider the multi-class classification setting from…
In classification models fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex.…