Paired-consistency: An example-based model-agnostic approach to fairness regularization in machine learning
Y Horesh, N Haas, E Mishraky, YS Resheff… - Machine Learning and …, 2020 - Springer
As AI systems develop in complexity it is becoming increasingly hard to ensure non-
discrimination on the basis of protected attributes such as gender, age, and race. Many …
discrimination on the basis of protected attributes such as gender, age, and race. Many …
fairml: A Statistician's Take on Fair Machine Learning Modelling
M Scutari - arXiv preprint arXiv:2305.02009, 2023 - arxiv.org
The adoption of machine learning in applications where it is crucial to ensure fairness and
accountability has led to a large number of model proposals in the literature, largely …
accountability has led to a large number of model proposals in the literature, largely …
Robust fairness under covariate shift
Making predictions that are fair with regard to protected attributes (race, gender, age, etc.)
has become an important requirement for classification algorithms. Existing techniques …
has become an important requirement for classification algorithms. Existing techniques …
Auditing and achieving intersectional fairness in classification problems
Machine learning algorithms are extensively used to make increasingly more consequential
decisions about people, so achieving optimal predictive performance can no longer be the …
decisions about people, so achieving optimal predictive performance can no longer be the …
Metrics and methods for a systematic comparison of fairness-aware machine learning algorithms
Understanding and removing bias from the decisions made by machine learning models is
essential to avoid discrimination against unprivileged groups. Despite recent progress in …
essential to avoid discrimination against unprivileged groups. Despite recent progress in …
Unfair geometries: exactly solvable data model with fairness implications
Machine learning (ML) may be oblivious to human bias but it is not immune to its
perpetuation. Marginalisation and iniquitous group representation are often traceable in the …
perpetuation. Marginalisation and iniquitous group representation are often traceable in the …
Fair regression: Quantitative definitions and reduction-based algorithms
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 …
recidivism rate, while guaranteeing a quantitative notion of fairness with respect to a …
[PDF][PDF] Fairness-aware machine learning
J Dunkelau, M Leuschel - An Extensive Overview, 2019 - stups.hhu-hosting.de
We provide an overview of the state-of-the-art in fairnessaware machine learning and
examine a wide variety of research articles in the area. We survey different fairness notions …
examine a wide variety of research articles in the area. We survey different fairness notions …
A comparative study of fairness-enhancing interventions in machine learning
SA Friedler, C Scheidegger… - Proceedings of the …, 2019 - dl.acm.org
Computers are increasingly used to make decisions that have significant impact on people's
lives. Often, these predictions can affect different population subgroups disproportionately …
lives. Often, these predictions can affect different population subgroups disproportionately …
Nonconvex optimization for regression with fairness constraints
J Komiyama, A Takeda, J Honda… - … on machine learning, 2018 - proceedings.mlr.press
The unfairness of a regressor is evaluated by measuring the correlation between the
estimator and the sensitive attribute (eg, race, gender, age), and the coefficient of …
estimator and the sensitive attribute (eg, race, gender, age), and the coefficient of …