Automated decision systems are increasingly used to make consequential decisions in people's lives. Due to the sensitivity of the manipulated data and the resulting decisions …
JM Alvarez, AB Colmenarejo, A Elobaid… - Ethics and Information …, 2024 - Springer
The literature addressing bias and fairness in AI models (fair-AI) is growing at a fast pace, making it difficult for novel researchers and practitioners to have a bird's-eye view picture of …
J Gao, B Chou, ZR McCaw, H Thurston… - arXiv preprint arXiv …, 2024 - arxiv.org
OBJECTIVE: Ensuring that machine learning (ML) algorithms are safe and effective within all patient groups, and do not disadvantage particular patients, is essential to clinical decision …
M Abroshan, A Elliott… - … Conference on Artificial …, 2024 - proceedings.mlr.press
In several real-world applications (eg, online advertising, item recommendations, etc.) it may not be possible to release and share the real dataset due to privacy concerns. As a result …
In the last decade it became increasingly apparent the inability of technical metrics such as accuracy, sustainability, and non-regressiveness to well characterize the behavior of …
Decision support systems became ubiquitous in every aspect of human lives. Their reliance on increasingly complex and opaque machine learning models raises transparency and …
The increasing use of algorithms in allocating resources and services in both private industry and public administration has sparked discussions about their consequences for …
Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in …
Y Hu, Y Wu, L Zhang - arXiv preprint arXiv:2401.11288, 2024 - arxiv.org
This paper studies long-term fair machine learning which aims to mitigate group disparity over the long term in sequential decision-making systems. To define long-term fairness, we …