Fairness-Aware PAC Learning from Corrupted Data


Loading...

Date

2022

Publication Type

Journal Article

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Addressing fairness concerns about machine learning models is a crucial step towards their long-term adoption in real-world automated systems. While many approaches have been developed for training fair models from data, little is known about the robustness of these methods to data corruption. In this work we consider fairness-aware learning under worst-case data manipulations. We show that an adversary can in some situations force any learner to return an overly biased classifier, regardless of the sample size and with or without degrading accuracy, and that the strength of the excess bias increases for learning problems with underrepresented protected groups in the data. We also prove that our hardness results are tight up to constant factors. To this end, we study two natural learning algorithms that optimize for both accuracy and fairness and show that these algorithms enjoy guarantees that are order-optimal in terms of the corruption ratio and the protected groups frequencies in the large data limit.

Publication status

published

Editor

Book title

Volume

23

Pages / Article No.

160

Publisher

Microtome Publishing

Event

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Fairness; robustness; data poisoning; trustworthy machine learning; PAC learning

Organisational unit

02219 - ETH AI Center / ETH AI Center

Notes

Funding

Related publications and datasets