Research Area:  Machine Learning
Meta-learning has gained wide popularity as a training framework that is more data-efficient than traditional machine learning methods. However, its generalization ability in complex task distributions, such as multimodal tasks, has not been thoroughly studied. Recently, some studies on multimodality-based meta-learning have emerged. This survey provides a comprehensive overview of the multimodality-based meta-learning landscape in terms of the methodologies and applications. We first formalize the definition of meta-learning in multimodality, along with the research challenges in this growing field, such as how to enrich the input in few-shot learning (FSL) or zero-shot learning (ZSL) in multimodal scenarios and how to generalize the models to new tasks. We then propose a new taxonomy to discuss typical meta-learning algorithms in multimodal tasks systematically. We investigate the contributions of related papers and summarize them by our taxonomy. Finally, we propose potential research directions for this promising field.
Keywords:  
Multimodality
meta-learning
machine learning
few-shot learning (FSL)
zero-shot learning (ZSL)
Author(s) Name:  Yao Ma, Shilin Zhao, Weixiao Wang, Yaoman Li, Irwin King
Journal name:  Knowledge-Based Systems
Conferrence name:  
Publisher name:  Elsevier
DOI:  10.1016/j.knosys.2022.108976
Volume Information:  Volume 250, 17 August 2022, 108976
Paper Link:   https://www.sciencedirect.com/science/article/abs/pii/S0950705122004737