Structured Prediction with Partial Labelling through the Infimum Loss - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Structured Prediction with Partial Labelling through the Infimum Loss

Prediction structurée à partir de données partiellement annotées via la "perte minimale"

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

Abstract

Annotating datasets is one of the main costs in nowadays supervised learning. The goal of weak supervision is to enable models to learn using only forms of labelling which are cheaper to collect, as partial labelling. This is a type of incomplete annotation where, for each datapoint, supervision is cast as a set of labels containing the real one. The problem of supervised learning with partial labelling has been studied for specific instances such as classification, multi-label, ranking or segmentation, but a general framework is still missing. This paper provides a unified framework based on structured prediction and on the concept of infimum loss to deal with partial labelling over a wide family of learning problems and loss functions. The framework leads naturally to explicit algorithms that can be easily implemented and for which proved statistical consistency and learning rates. Experiments confirm the superiority of the proposed approach over commonly used baselines.
Fichier principal
Vignette du fichier
main.pdf (546.54 Ko) Télécharger le fichier
tex_files.zip (1.41 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Origin Files produced by the author(s)

Dates and versions

hal-03127110 , version 1 (01-02-2021)

Licence

Identifiers

  • HAL Id : hal-03127110 , version 1

Cite

Vivien Cabannes, Alessandro Rudi, Francis Bach. Structured Prediction with Partial Labelling through the Infimum Loss. ICML 2020 - 37th International Conference on Machine Learning, Jul 2020, Online, United States. pp.1230-1239. ⟨hal-03127110⟩
254 View
74 Download

Share

Gmail Mastodon Facebook X LinkedIn More