Fairness-aware PAC learning from corrupted data

Konstantinov NH, Lampert C. 2022. Fairness-aware PAC learning from corrupted data. Journal of Machine Learning Research. 23, 1–60.

Download
OA 2022_JournalMachineLearningResearch_Konstantinov.pdf 551.86 KB
Journal Article | Published | English

Scopus indexed
Department
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.
Publishing Year
Date Published
2022-05-01
Journal Title
Journal of Machine Learning Research
Acknowledgement
The authors thank Eugenia Iofinova and Bernd Prach for providing feedback on early versions of this paper. This publication was made possible by an ETH AI Center postdoctoral fellowship to Nikola Konstantinov.
Volume
23
Page
1-60
ISSN
eISSN
IST-REx-ID

Cite this

Konstantinov NH, Lampert C. Fairness-aware PAC learning from corrupted data. Journal of Machine Learning Research. 2022;23:1-60.
Konstantinov, N. H., & Lampert, C. (2022). Fairness-aware PAC learning from corrupted data. Journal of Machine Learning Research.
Konstantinov, Nikola H, and Christoph Lampert. “Fairness-Aware PAC Learning from Corrupted Data.” Journal of Machine Learning Research, 2022.
N. H. Konstantinov and C. Lampert, “Fairness-aware PAC learning from corrupted data,” Journal of Machine Learning Research, vol. 23. pp. 1–60, 2022.
Konstantinov NH, Lampert C. 2022. Fairness-aware PAC learning from corrupted data. Journal of Machine Learning Research. 23, 1–60.
Konstantinov, Nikola H., and Christoph Lampert. “Fairness-Aware PAC Learning from Corrupted Data.” Journal of Machine Learning Research, vol. 23, 2022, pp. 1–60.
All files available under the following license(s):
Creative Commons Attribution 4.0 International Public License (CC-BY 4.0):
Main File(s)
Access Level
OA Open Access
Date Uploaded
2022-07-12
MD5 Checksum
9cac897b54a0ddf3a553a2c33e88cfda


Material in ISTA:
Dissertation containing ISTA record

Export

Marked Publications

Open Data ISTA Research Explorer

Sources

arXiv 2102.06004

Search this title in

Google Scholar