Timezone: »

Fair Classification with Noisy Protected Attributes: A Framework with Provable Guarantees
L. Elisa Celis · Lingxiao Huang · Vijay Keswani · Nisheeth K. Vishnoi

Wed Jul 21 09:00 PM -- 11:00 PM (PDT) @ Virtual

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.

Author Information

L. Elisa Celis (Yale)
Lingxiao Huang (Tsinghua University)
Vijay Keswani (Yale University)
Nisheeth K. Vishnoi (Yale University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors