English
Related papers

Related papers: Estimating and Implementing Conventional Fairness …

200 papers

The measurement of bias in machine learning often focuses on model performance across identity subgroups (such as man and woman) with respect to groundtruth labels. However, these methods do not directly measure the associations that a…

Computer Vision and Pattern Recognition · Computer Science 2021-06-08 Osman Aka , Ken Burke , Alex Bäuerle , Christina Greer , Margaret Mitchell

Machine learning models are vulnerable to biases that result in unfair treatment of individuals from different populations. Recent work that aims to test a model's fairness at the individual level either relies on domain knowledge to choose…

Machine Learning · Statistics 2022-10-13 Giuseppe Castiglione , Ga Wu , Christopher Srinivasa , Simon Prince

Data sets for fairness relevant tasks can lack examples or be biased according to a specific label in a sensitive attribute. We demonstrate the usefulness of weight based meta-learning approaches in such situations. For models that can be…

Machine Learning · Computer Science 2019-11-12 Dylan Slack , Sorelle Friedler , Emile Givental

This thesis scrutinizes common assumptions underlying traditional machine learning approaches to fairness in consequential decision making. After challenging the validity of these assumptions in real-world applications, we propose ways to…

Machine Learning · Computer Science 2021-02-01 Niki Kilbertus

Motivated by the recital (67) of the current corrigendum of the AI Act in the European Union, we propose and present measures and mitigation strategies for discrimination in tabular datasets. We specifically focus on datasets that contain…

Machine Learning · Computer Science 2024-11-05 Manh Khoi Duong , Stefan Conrad

This paper presents novel experiments shedding light on the shortcomings of current metrics for assessing biases of gender discrimination made by machine learning algorithms on textual data. We focus on the Bios dataset, and our learning…

Computation and Language · Computer Science 2023-06-09 Fanny Jourdan , Laurent Risser , Jean-Michel Loubes , Nicholas Asher

As an important problem in modern data analytics, classification has witnessed varieties of applications from different domains. Different from conventional classification approaches, fair classification concerns the issues of unintentional…

Machine Learning · Statistics 2020-12-25 Qing Ye , Weijun Xie

Real-world applications of machine learning tools in high-stakes domains are often regulated to be fair, in the sense that the predicted target should satisfy some quantitative notion of parity with respect to a protected attribute.…

Machine Learning · Computer Science 2021-10-06 Han Zhao

Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, considering very narrow data conditions. For instance, the effect of…

Machine Learning · Computer Science 2022-10-18 Xudong Han , Aili Shen , Trevor Cohn , Timothy Baldwin , Lea Frermann

Long-term fairness algorithms aim to satisfy fairness beyond static and short-term notions by accounting for the dynamics between decision-making policies and population behavior. Most previous approaches evaluate performance and fairness…

Machine Learning · Computer Science 2026-05-22 Giovani Valdrighi , Isabel Valera , Marcos Medeiros Raimundo

The notion of individual fairness requires that similar people receive similar treatment. However, this is hard to achieve in practice since it is difficult to specify the appropriate similarity metric. In this work, we attempt to learn…

Computers and Society · Computer Science 2019-11-01 Hanchen Wang , Nina Grgic-Hlaca , Preethi Lahoti , Krishna P. Gummadi , Adrian Weller

Group fairness requires that different protected groups, characterized by a given sensitive attribute, receive equal outcomes overall. Typically, the level of group fairness is measured by the statistical gap between predictions from…

Artificial Intelligence · Computer Science 2025-01-07 Kunwoong Kim , Insung Kong , Jongjin Lee , Minwoo Chae , Sangchul Park , Yongdai Kim

Fairness testing evaluates whether a model satisfies a specified fairness criterion across different groups, yet most research has focused on classification models, leaving regression models underexplored. This paper introduces a framework…

Machine Learning · Computer Science 2026-02-11 Wanxin Li , Yongjin P. Park , Khanh Dao Duc

Although effective deepfake detection models have been developed in recent years, recent studies have revealed that these models can result in unfair performance disparities among demographic groups, such as race and gender. This can lead…

Computer Vision and Pattern Recognition · Computer Science 2024-03-03 Li Lin , Xinan He , Yan Ju , Xin Wang , Feng Ding , Shu Hu

Understanding and removing bias from the decisions made by machine learning models is essential to avoid discrimination against unprivileged groups. Despite recent progress in algorithmic fairness, there is still no clear answer as to which…

Optimizing prediction accuracy can come at the expense of fairness. Towards minimizing discrimination against a group, fair machine learning algorithms strive to equalize the behavior of a model across different groups, by imposing a…

Machine Learning · Statistics 2020-06-17 Hongyan Chang , Ta Duy Nguyen , Sasi Kumar Murakonda , Ehsan Kazemi , Reza Shokri

Classical PAC generalization bounds on the prediction risk of a classifier are insufficient to provide theoretical guarantees on fairness when the goal is to learn models balancing predictive risk and fairness constraints. We propose a…

We study fair classification in the presence of an omniscient adversary that, given an $\eta$, is allowed to choose an arbitrary $\eta$-fraction of the training samples and arbitrarily perturb their protected attributes. The motivation…

Machine Learning · Computer Science 2021-11-24 L. Elisa Celis , Anay Mehrotra , Nisheeth K. Vishnoi

Artificial-intelligence systems are becoming ubiquitous in society, yet their predictions typically inherit biases with respect to protected attributes such as race, gender, or age. Classical fairness notions, most notably Statistical…

Machine Learning · Statistics 2026-05-08 Filip Edström , Guilherme W. F. Barros , Tetiana Gorbach , Xavier de Luna

Bias-transforming methods of fairness-aware machine learning aim to correct a non-neutral status quo with respect to a protected attribute (PA). Current methods, however, lack an explicit formulation of what drives non-neutrality. We…

Machine Learning · Computer Science 2025-02-04 Ludwig Bothmann , Philip A. Boustani , Jose M. Alvarez , Giuseppe Casalicchio , Bernd Bischl , Susanne Dandl