S Caton, C Haas - ACM Computing Surveys, 2024 - dl.acm.org
When Machine Learning technologies are used in contexts that affect citizens, companies as well as researchers need to be confident that there will not be any unexpected social …
The rapid development of Artificial Intelligence (AI) technology has enabled the deployment of various systems based on it. However, many current AI systems are found vulnerable to …
This article provides a comprehensive survey of bias mitigation methods for achieving fairness in Machine Learning (ML) models. We collect a total of 341 publications concerning …
The separation between training and deployment of machine learning models implies that not all scenarios encountered in deployment can be anticipated during training, and …
YC Tan, LE Celis - Advances in neural information …, 2019 - proceedings.neurips.cc
Social bias in machine learning has drawn significant attention, with work ranging from demonstrations of bias in a multitude of applications, curating definitions of fairness for …
S Bera, D Chakrabarty, N Flores… - Advances in Neural …, 2019 - proceedings.neurips.cc
We study the problem of finding low-cost {\em fair clusterings} in data where each data point may belong to many protected groups. Our work significantly generalizes the seminal work …
N Kozodoi, J Jacob, S Lessmann - European Journal of Operational …, 2022 - Elsevier
The rise of algorithmic decision-making has spawned much research on fair machine learning (ML). Financial institutions use ML for building risk scorecards that support a range …
Studies conducted on Western, Educated, Industrialized, Rich, and Democratic (WEIRD) samples are considered atypical of the world's population and may not accurately represent …
S Dutta, D Wei, H Yueksel, PY Chen… - International …, 2020 - proceedings.mlr.press
A trade-off between accuracy and fairness is almost taken as a given in the existing literature on fairness in machine learning. Yet, it is not preordained that accuracy should decrease …