H Hu, C Lan - The AAAI Workshop on Privacy-Preserving Artificial …, 2020 - par.nsf.gov
Fairness and privacy are both significant social norms in machine learning. In (Hu et al 2019), we propose a distributed framework to learn fair prediction models while protecting …
Machine learning models have demonstrated promising performance in many areas. However, the concerns that they can be biased against specific demographic groups hinder …
Fairness-aware learning aims at constructing classifiers that not only make accurate predictions, but also do not discriminate against specific groups. It is a fast-growing area of …
T Jang, P Shi, X Wang - Proceedings of the AAAI Conference on …, 2022 - ojs.aaai.org
The fairness in machine learning is getting increasing attention, as its applications in different fields continue to expand and diversify. To mitigate the discriminated model …
Fair machine learning methods seek to train models that balance model performance across demographic subgroups defined over sensitive attributes like race and gender. Although …
Y Zeng, H Chen, K Lee - arXiv preprint arXiv:2110.15545, 2021 - arxiv.org
Recently, lots of algorithms have been proposed for learning a fair classifier from decentralized data. However, many theoretical and algorithmic questions remain open. First …
We propose differential fairness, a multi-attribute definition of fairness in machine learning which is informed by intersectionality, a critical lens arising from the humanities literature …
Most existing fair classifiers rely on sensitive attributes to achieve fairness. However, for many scenarios, we cannot obtain sensitive attributes due to privacy and legal issues. The …
Machine learning algorithms are increasingly used to make or support important decisions about people's lives. This has led to interest in the problem of fair classification, which …