A survey of deep meta-learning

By Mike Huisman, Jan N. van Rijn, Aske Plaat. Artificial Intelligence Review, 2020

418 citations recorded by the source corpus.

Deep neural networks can achieve great successes when presented with large data sets and sufficient computational resources. However, their ability to learn new concepts quickly is limited. Meta-learning is one approach to address this issue, by enabling the network to learn how to learn. The field of Deep Meta-Learning advances at great speed, but lacks a unified, in-depth overview of current techniques. With this work, we aim to bridge this gap. After providing the reader with a theoretical foundation, we investigate and summarize key methods, which are categorized into (i) metric-, (ii) model-, and (iii) optimization-based techniques. In addition, we identify the main open challenges, such as performance evaluations on heterogeneous benchmarks, and reduction of the computational costs of meta-learning.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/332c44793b70776b9b966128c52e694222b1ab73

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Chengyu Wang
2. Jun Huang
3. Ming Gao
4. Minghui Qiu
5. Jianing Wang

In Computer Vision and Pattern Recognition

1. Minghui Qiu

Citations in the corpus

• TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text Classification (2021, background): “In machine learning, the meta-learning paradigm is extensively studied, which produces models that are capable of being adapted to a group of similar tasks quickly with few learning steps (Wang et al., 2020c; Huisman et al., 2020).”