The reviewed record of science sign in
Pith

arxiv: 2106.02968 · v4 · pith:PGR4MNC7 · submitted 2021-06-05 · cs.LG · math.OC

Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:PGR4MNC7record.jsonopen to challenge →

classification cs.LG math.OC
keywords datalearningpoolunlabeledactiveapproachbudgetcore
0
0 comments X
read the original abstract

Active learning is the process of training a model with limited labeled data by selecting a core subset of an unlabeled data pool to label. The large scale of data sets used in deep learning forces most sample selection strategies to employ efficient heuristics. This paper introduces an integer optimization problem for selecting a core set that minimizes the discrete Wasserstein distance from the unlabeled pool. We demonstrate that this problem can be tractably solved with a Generalized Benders Decomposition algorithm. Our strategy uses high-quality latent features that can be obtained by unsupervised learning on the unlabeled pool. Numerical results on several data sets show that our optimization approach is competitive with baselines and particularly outperforms them in the low budget regime where less than one percent of the data set is labeled.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.