Active approximately metric-fair learning

Yiting Cao, Chao Lan
Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, PMLR 180:275-285, 2022.

Abstract

Existing studies on individual fairness focus on the passive setting and typically require $O(\frac{1}{\varepsilon^2})$ labeled instances to achieve an $\varepsilon$ bias budget. In this paper, we build on the elegant Approximately Metric-Fair (AMF) learning framework and propose an active AMF learner that can provably achieve the same budget with only $O(\log \frac{1}{\varepsilon})$ labeled instances. To our knowledge, this is a first and substantial improvement of the existing sample complexity for achieving individual fairness. Through experiments on three data sets, we show the proposed active AMF learner improves fairness on linear and non-linear models more efficiently than its passive counterpart as well as state-of-the-art active learners, while maintaining a comparable accuracy. To facilitate algorithm design and analysis, we also design a provably equivalent form of the approximate metric fairness based on uniform continuity instead of the existing almost Lipschitz continuity.

Cite this Paper

BibTeX
@InProceedings{pmlr-v180-cao22a, title = {Active approximately metric-fair learning}, author = {Cao, Yiting and Lan, Chao}, booktitle = {Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence}, pages = {275--285}, year = {2022}, editor = {Cussens, James and Zhang, Kun}, volume = {180}, series = {Proceedings of Machine Learning Research}, month = {01--05 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v180/cao22a/cao22a.pdf}, url = {https://proceedings.mlr.press/v180/cao22a.html}, abstract = {Existing studies on individual fairness focus on the passive setting and typically require $O(\frac{1}{\varepsilon^2})$ labeled instances to achieve an $\varepsilon$ bias budget. In this paper, we build on the elegant Approximately Metric-Fair (AMF) learning framework and propose an active AMF learner that can provably achieve the same budget with only $O(\log \frac{1}{\varepsilon})$ labeled instances. To our knowledge, this is a first and substantial improvement of the existing sample complexity for achieving individual fairness. Through experiments on three data sets, we show the proposed active AMF learner improves fairness on linear and non-linear models more efficiently than its passive counterpart as well as state-of-the-art active learners, while maintaining a comparable accuracy. To facilitate algorithm design and analysis, we also design a provably equivalent form of the approximate metric fairness based on uniform continuity instead of the existing almost Lipschitz continuity. } }
Endnote
%0 Conference Paper %T Active approximately metric-fair learning %A Yiting Cao %A Chao Lan %B Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2022 %E James Cussens %E Kun Zhang %F pmlr-v180-cao22a %I PMLR %P 275--285 %U https://proceedings.mlr.press/v180/cao22a.html %V 180 %X Existing studies on individual fairness focus on the passive setting and typically require $O(\frac{1}{\varepsilon^2})$ labeled instances to achieve an $\varepsilon$ bias budget. In this paper, we build on the elegant Approximately Metric-Fair (AMF) learning framework and propose an active AMF learner that can provably achieve the same budget with only $O(\log \frac{1}{\varepsilon})$ labeled instances. To our knowledge, this is a first and substantial improvement of the existing sample complexity for achieving individual fairness. Through experiments on three data sets, we show the proposed active AMF learner improves fairness on linear and non-linear models more efficiently than its passive counterpart as well as state-of-the-art active learners, while maintaining a comparable accuracy. To facilitate algorithm design and analysis, we also design a provably equivalent form of the approximate metric fairness based on uniform continuity instead of the existing almost Lipschitz continuity.
APA
Cao, Y. & Lan, C.. (2022). Active approximately metric-fair learning. Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 180:275-285 Available from https://proceedings.mlr.press/v180/cao22a.html.

Related Material