Disambiguation of Weak Supervision Leading to Exponential Convergence Rates
Abstract
Machine learning approached through supervised learning requires expensive annotation of data. This motivates weakly supervised learning, where data are annotated with incomplete yet discriminative information. In this paper, we focus on partial labelling, an instance of weak supervision where, from a given input, we are given a set of potential targets. We review a disambiguation principle to recover full supervision from weak supervision, and propose an empirical disambiguation algorithm. We prove exponential convergence rates of our algorithm under classical learnability assumptions, and we illustrate the usefulness of our method on practical examples.
Cite
Text
Cabannnes et al. "Disambiguation of Weak Supervision Leading to Exponential Convergence Rates." International Conference on Machine Learning, 2021.Markdown
[Cabannnes et al. "Disambiguation of Weak Supervision Leading to Exponential Convergence Rates." International Conference on Machine Learning, 2021.](https://mlanthology.org/icml/2021/cabannnes2021icml-disambiguation/)BibTeX
@inproceedings{cabannnes2021icml-disambiguation,
title = {{Disambiguation of Weak Supervision Leading to Exponential Convergence Rates}},
author = {Cabannnes, Vivien A and Bach, Francis and Rudi, Alessandro},
booktitle = {International Conference on Machine Learning},
year = {2021},
pages = {1147-1157},
volume = {139},
url = {https://mlanthology.org/icml/2021/cabannnes2021icml-disambiguation/}
}