Estimating Labels from Label Proportions

Abstract

Consider the following problem: given sets of unlabeled observations, each set with known label proportions, predict the labels of another set of observations, possibly with known label proportions. This problem occurs in areas like e-commerce, politics, spam filtering and improper content detection. We present consistent estimators which can reconstruct the correct labels with high probability in a uniform convergence sense. Experiments show that our method works well in practice.

Cite

Text

Quadrianto et al. "Estimating Labels from Label Proportions." Journal of Machine Learning Research, 2009.

Markdown

[Quadrianto et al. "Estimating Labels from Label Proportions." Journal of Machine Learning Research, 2009.](https://mlanthology.org/jmlr/2009/quadrianto2009jmlr-estimating/)

BibTeX

@article{quadrianto2009jmlr-estimating,
  title     = {{Estimating Labels from Label Proportions}},
  author    = {Quadrianto, Novi and Smola, Alex J. and Caetano, Tibério S. and Le, Quoc V.},
  journal   = {Journal of Machine Learning Research},
  year      = {2009},
  pages     = {2349-2374},
  volume    = {10},
  url       = {https://mlanthology.org/jmlr/2009/quadrianto2009jmlr-estimating/}
}