A Meta-Learning Approach to One-Step Active Learning - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

A Meta-Learning Approach to One-Step Active Learning

Résumé

We consider the problem of learning when obtaining the training labels is costly, which is usually tackled in the literature using active-learning techniques. These approaches provide strategies to choose the examples to label before or during training. These strategies are usually based on heuristics or even theoretical measures, but are not learned as they are directly used during training. We design a model which aims at \textit{learning active-learning strategies} using a meta-learning setting. More specifically, we consider a pool-based setting, where the system observes all the examples of the dataset of a problem and has to choose the subset of examples to label in a single shot. Experiments show encouraging results.

Dates et versions

hal-01690004 , version 1 (22-01-2018)

Identifiants

Citer

Gabriella Contardo, Ludovic Denoyer, Thierry Artières. A Meta-Learning Approach to One-Step Active Learning. 2018. ⟨hal-01690004⟩
236 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More