A Meta-Learning Approach to One-Step Active Learning

Abstract : 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.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01690004
Contributor : Thierry Artieres <>
Submitted on : Monday, January 22, 2018 - 3:49:04 PM
Last modification on : Friday, July 5, 2019 - 3:26:03 PM

Links full text

Identifiers

  • HAL Id : hal-01690004, version 1
  • ARXIV : 1706.08334

Citation

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

Share

Metrics

Record views

326