Machine Learning (ML) software has been widely adopted in modern society, with reported fairness implications for minority groups based on race, sex, age, etc. Many recent works …
Q Zhang, J Liu, Z Zhang, J Wen… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
In the literature of mitigating unfairness in machine learning (ML), many fairness measures are designed to evaluate predictions of learning models and also utilized to guide the …
There are several bias mitigators that can reduce algorithmic bias in machine learning models but, unfortunately, the effect of mitigators on fairness is often not stable when …
One of the main challenges of machine learning is to ensure that its applications do not generate or propagate unfair discrimination based on sensitive characteristics such as …
Fairness has become an essential problem in many domains of Machine Learning (ML), such as classification, natural language processing, and Generative Adversarial Networks …
Machine Learning (ML) models trained on biased data can reproduce and even amplify these biases. Since such models are deployed to make decisions that can affect people's …
Bias mitigators can improve algorithmic fairness in machine learning models, but their effect on fairness is often not stable across data splits. A popular approach to train more stable …
A Freitas, J Brookhouse - Handbook of Evolutionary Machine Learning, 2023 - Springer
At present, supervised machine learning algorithms are ubiquitously used to learn predictive models that have a major impact on people's lives. However, the vast majority of such …
Machine learning is becoming ubiquitous. From finance to medicine, machine learning models are boosting decision-making processes and even outperforming humans in some …