Open Access
June 2015 Weakly supervised clustering: Learning fine-grained signals from coarse labels
Stefan Wager, Alexander Blocker, Niall Cardin
Ann. Appl. Stat. 9(2): 801-820 (June 2015). DOI: 10.1214/15-AOAS812


Consider a classification problem where we do not have access to labels for individual training examples, but only have average labels over subpopulations. We give practical examples of this setup and show how such a classification task can usefully be analyzed as a weakly supervised clustering problem. We propose three approaches to solving the weakly supervised clustering problem, including a latent variables model that performs well in our experiments. We illustrate our methods on an analysis of aggregated elections data and an industry data set that was the original motivation for this research.


Download Citation

Stefan Wager. Alexander Blocker. Niall Cardin. "Weakly supervised clustering: Learning fine-grained signals from coarse labels." Ann. Appl. Stat. 9 (2) 801 - 820, June 2015.


Received: 1 June 2014; Revised: 1 February 2015; Published: June 2015
First available in Project Euclid: 20 July 2015

zbMATH: 06499931
MathSciNet: MR3371336
Digital Object Identifier: 10.1214/15-AOAS812

Keywords: Latent variables model , uncertain class label

Rights: Copyright © 2015 Institute of Mathematical Statistics

Vol.9 • No. 2 • June 2015
Back to Top