Related papers: FlipTest: Fairness Testing via Optimal Transport

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…

We investigate performance disparities in deep classifiers. We find that the ability of classifiers to separate individuals into subgroups varies substantially across medical imaging modalities and protected characteristics; crucially, we…

How can we control for latent discrimination in predictive models? How can we provably remove it? Such questions are at the heart of algorithmic fairness and its impacts on society. In this paper, we define a new operational fairness…

Algorithmic fairness in lending today relies on group fairness metrics for monitoring statistical parity across protected groups. This approach is vulnerable to subgroup discrimination by proxy, carrying significant risks of legal and…

Covariate shift in the test data is a common practical phenomena that can significantly downgrade both the accuracy and the fairness performance of the model. Ensuring fairness across different sensitive groups under covariate shift is of…

In this paper, we study the problem of fair classification in the presence of prior probability shifts, where the training set distribution differs from the test set. This phenomenon can be observed in the yearly records of several…

Scoring systems, as a type of predictive model, have significant advantages in interpretability and transparency and facilitate quick decision-making. As such, scoring systems have been extensively used in a wide variety of industries such…

Optimal transport is a powerful framework for the efficient allocation of resources between sources and targets. However, traditional models often struggle to scale effectively in the presence of large and heterogeneous populations. In this…

Fairness has been a critical issue that affects the adoption of deep learning models in real practice. To improve model fairness, many existing methods have been proposed and evaluated to be effective in their own contexts. However, there…

Item Response Theory (IRT) has been widely used in educational psychometrics to assess student ability, as well as the difficulty and discrimination of test questions. In this context, discrimination specifically refers to how effectively a…

Systemic bias with respect to gender, race and ethnicity, often unconscious, is prevalent in datasets involving choices among individuals. Consequently, society has found it challenging to alleviate bias and achieve diversity in a way that…

Machine learning systems are often trained and evaluated for fairness on historical data, yet deployed in environments where conditions have shifted. A particularly common form of shift occurs when the prevalence of positive outcomes…

Increasingly, discrimination by algorithms is perceived as a societal and legal problem. As a response, a number of criteria for implementing algorithmic fairness in machine learning have been developed in the literature. This paper…

The issue of fairness in machine learning stems from the fact that historical data often displays biases against specific groups of people which have been underprivileged in the recent past, or still are. In this context, one of the…

We study the problem of post-processing a supervised machine-learned regressor to maximize fair binary classification at all decision thresholds. By decreasing the statistical distance between each group's score distributions, we show that…

Identifying the causes of a model's unfairness is an important yet relatively unexplored task. We look into this problem through the lens of training data - the major source of unfairness. We ask the following questions: How would the…

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…

In this work, we define and solve the Fair Top-k Ranking problem, in which we want to determine a subset of k candidates from a large pool of n >> k candidates, maximizing utility (i.e., select the "best" candidates) subject to group…

Providing various machine learning (ML) applications in the real world, concerns about discrimination hidden in ML models are growing, particularly in high-stakes domains. Existing techniques for assessing the discrimination level of ML…

Previous post-processing bias mitigation algorithms on both group and individual fairness don't work on regression models and datasets with multi-class numerical labels. We propose a priority-based post-processing bias mitigation on both…