TY - GEN
T1 - A Survey of Meta-learning for Classification Tasks
AU - Zhang, Yue
AU - Wei, Baoguo
AU - Li, Xu
AU - Li, Lixin
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 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.
AB - 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.
KW - classification
KW - few-shot learning
KW - meta learning
KW - unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85161860054&partnerID=8YFLogxK
U2 - 10.1109/ISCTech58360.2022.00075
DO - 10.1109/ISCTech58360.2022.00075
M3 - 会议稿件
AN - SCOPUS:85161860054
T3 - Proceedings - 2022 10th International Conference on Information Systems and Computing Technology, ISCTech 2022
SP - 442
EP - 449
BT - Proceedings - 2022 10th International Conference on Information Systems and Computing Technology, ISCTech 2022
A2 - Zhang, Lei
A2 - Li, Lixin
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 10th International Conference on Information Systems and Computing Technology, ISCTech 2022
Y2 - 28 December 2022 through 30 December 2022
ER -