Logo du site
  • English
  • Français
  • Se connecter
Logo du site
  • English
  • Français
  • Se connecter
  1. Accueil
  2. Université de Neuchâtel
  3. Publications
  4. Cost-Minimising Strategies for Data Labelling: Optimal Stopping and Active Learning
 
  • Details
Options
Vignette d'image

Cost-Minimising Strategies for Data Labelling: Optimal Stopping and Active Learning

Auteur(s)
Dimitrakakis, Christos 
Institut d'informatique 
Christian Savu-Krohn
Date de parution
2008
In
Lecture Notes in Computer Science
Foundations of Information and Knowledge Systems
De la page
96
A la page
111
Mots-clés
  • Active Learning
  • Data Labelling
  • Generalisation Error
  • Convergence Curve
  • Decision Stump
  • Active Learning

  • Data Labelling

  • Generalisation Error

  • Convergence Curve

  • Decision Stump

Résumé
Supervised learning deals with the inference of a distribution over an output or label space Y conditioned on points in an observation space X, given a training dataset D of pairs in X×Y.
However, in a lot of applications of interest, acquisition of large amounts of observations is easy, while the process of generating labels is time-consuming or costly. One way to deal with this problem is active learning, where points to be labelled are selected with the aim of creating a model with better performance than that of an model trained on an equal number of randomly sampled points. In this paper, we instead propose to deal with the labelling cost directly: The learning goal is defined as the minimisation of a cost which is a function of the expected model performance and the total cost of the labels used. This allows the development of general strategies and specific algorithms for (a) optimal stopping, where the expected cost dictates whether label acquisition should continue (b) empirical evaluation, where the cost is used as a performance metric for a given combination of inference, stopping and sampling methods. Though the main focus of the paper is optimal stopping, we also aim to provide the background for further developments and discussion in the related field of active learning.
Identifiants
https://libra.unine.ch/handle/123456789/30997
_
10.1007/978-3-540-77684-0_9
_
9783540776833
9783540776840
Type de publication
book part
Dossier(s) à télécharger
 main article: 0708.1242.pdf (304.19 KB)
google-scholar
Présentation du portailGuide d'utilisationStratégie Open AccessDirective Open Access La recherche à l'UniNE Open Access ORCIDNouveautés

Service information scientifique & bibliothèques
Rue Emile-Argand 11
2000 Neuchâtel
contact.libra@unine.ch

Propulsé par DSpace, DSpace-CRIS & 4Science | v2022.02.00