Disambiguation of Weak Supervision leading to Exponential Convergence rates - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Disambiguation of Weak Supervision leading to Exponential Convergence rates

Vivien Cabannes
  • Function : Author
  • PersonId : 1089863
Francis Bach

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.
Fichier principal
Vignette du fichier
2102.02789.pdf (792.05 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03383710 , version 1 (23-10-2021)

Identifiers

  • HAL Id : hal-03383710 , version 1

Cite

Vivien Cabannes, Alessandro Rudi, Francis Bach. Disambiguation of Weak Supervision leading to Exponential Convergence rates. ICML 2021 - 38th International Conference on Machine Learning, Jul 2021, Virtual, France. pp.1147-1157. ⟨hal-03383710⟩
16 View
41 Download

Share

Gmail Mastodon Facebook X LinkedIn More