Metric-Fair Active Learning

Jie Shen · Nan Cui · Jing Wang

Hall E #1224

Keywords: [ T: Active Learning and Interactive Learning ]

[ Abstract ]
[ Poster [ Paper PDF
Wed 20 Jul 3:30 p.m. PDT — 5:30 p.m. PDT
Spotlight presentation: Theory
Wed 20 Jul 10:15 a.m. PDT — 11:45 a.m. PDT


Active learning has become a prevalent technique for designing label-efficient algorithms, where the central principle is to only query and fit ``informative'' labeled instances. It is, however, known that an active learning algorithm may incur unfairness due to such instance selection procedure. In this paper, we henceforth study metric-fair active learning of homogeneous halfspaces, and show that under the distribution-dependent PAC learning model, fairness and label efficiency can be achieved simultaneously. We further propose two extensions of our main results: 1) we show that it is possible to make the algorithm robust to the adversarial noise~--~one of the most challenging noise models in learning theory; and 2) it is possible to significantly improve the label complexity when the underlying halfspace is sparse.

Chat is not available.