Skip to yearly menu bar Skip to main content


Poster

Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees

L. Elisa Celis · Lingxiao Huang · Vijay Keswani · Nisheeth K. Vishnoi

Virtual

Keywords: [ Fairness, Accountability, and Transparency ] [ Social Aspects of Machine Learning ]


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.

Chat is not available.