A Survey of Meta-learning for Classification Tasks

Yue Zhang, Baoguo Wei, Xu Li, Lixin Li

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

The superior performance of deep learning is supported by massive data and powerful computing engines. Meta-learning is an imitation of human learning ability. Instead of relying on massive quantities of data or numerous trials to learn features of current tasks, general knowledge obtained from historical tasks will be applied to future unknown tasks during meta-learning. Thus, it is considered one of the keys to achieving general artificial intelligence. In conjunction with the classification problem, meta-learning has had a new advancement recently, which is reviewed in this paper. First, the general settings and current formal definition of meta-learning are described. Then, the current methods in this field are summarized. The latest directions-methods based on data augmentation, transfer-learning, and unsupervised or semi-supervised learning are described in detail. Additionally, the quantitative performance of the examined approaches is assessed using benchmark datasets for categorization tasks facing small samples. Finally, it is proposed that the potential of meta-learning can be thoroughly explored from three perspectives: cross-domain adaptability, breakthrough of task space, and cost reduction.

Original languageEnglish
Title of host publicationProceedings - 2022 10th International Conference on Information Systems and Computing Technology, ISCTech 2022
EditorsLei Zhang, Lixin Li
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages442-449
Number of pages8
ISBN (Electronic)9798350332933
DOIs
StatePublished - 2022
Event10th International Conference on Information Systems and Computing Technology, ISCTech 2022 - Virtual, Online, China
Duration: 28 Dec 202230 Dec 2022

Publication series

NameProceedings - 2022 10th International Conference on Information Systems and Computing Technology, ISCTech 2022

Conference

Conference10th International Conference on Information Systems and Computing Technology, ISCTech 2022
Country/TerritoryChina
CityVirtual, Online
Period28/12/2230/12/22

Keywords

  • classification
  • few-shot learning
  • meta learning
  • unsupervised learning

Fingerprint

Dive into the research topics of 'A Survey of Meta-learning for Classification Tasks'. Together they form a unique fingerprint.

Cite this