Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bae, Wonho, Wang, Jing, Sutherland, Danica J.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914885774868480
author Bae, Wonho
Wang, Jing
Sutherland, Danica J.
author_facet Bae, Wonho
Wang, Jing
Sutherland, Danica J.
contents Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided. In some settings, however, it is feasible to actively select which points to label; the potential gain from a careful choice is substantial, but the setting requires major differences from typical active learning setups. We clarify the ways in which active meta-learning can be used to label a context set, depending on which parts of the meta-learning process use active learning. Within this framework, we propose a natural algorithm based on fitting Gaussian mixtures for selecting which points to label; though simple, the algorithm also has theoretical motivation. The proposed algorithm outperforms state-of-the-art active learning methods when used with various meta-learning algorithms across several benchmark datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2311_02879
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling
Bae, Wonho
Wang, Jing
Sutherland, Danica J.
Machine Learning
Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided. In some settings, however, it is feasible to actively select which points to label; the potential gain from a careful choice is substantial, but the setting requires major differences from typical active learning setups. We clarify the ways in which active meta-learning can be used to label a context set, depending on which parts of the meta-learning process use active learning. Within this framework, we propose a natural algorithm based on fitting Gaussian mixtures for selecting which points to label; though simple, the algorithm also has theoretical motivation. The proposed algorithm outperforms state-of-the-art active learning methods when used with various meta-learning algorithms across several benchmark datasets.
title Exploring Active Learning in Meta-Learning: Enhancing Context Set Labeling
topic Machine Learning
url https://arxiv.org/abs/2311.02879