Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees
Abstract
We present an optimization framework for learning a fair classifier in the presence of noisy perturbations in the protected attributes. Compared to prior work, our framework can be employed with a very general class of linear and linear-fractional fairness constraints, can handle multiple, non-binary protected attributes, and outputs a classifier that comes with provable guarantees on both accuracy and fairness. Empirically, we show that our framework can be used to attain either statistical rate or false positive rate fairness guarantees with a minimal loss in accuracy, even when the noise is large, in two real-world datasets.
Cite
Text
Celis et al. "Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees." International Conference on Machine Learning, 2021.Markdown
[Celis et al. "Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees." International Conference on Machine Learning, 2021.](https://mlanthology.org/icml/2021/celis2021icml-fair/)BibTeX
@inproceedings{celis2021icml-fair,
title = {{Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees}},
author = {Celis, L. Elisa and Huang, Lingxiao and Keswani, Vijay and Vishnoi, Nisheeth K.},
booktitle = {International Conference on Machine Learning},
year = {2021},
pages = {1349-1361},
volume = {139},
url = {https://mlanthology.org/icml/2021/celis2021icml-fair/}
}