When Meta-Learning Meets Online and Continual Learning: A Survey

TL;DR

This survey comprehensively reviews the intersection of meta-learning, online learning, and continual learning, clarifying their distinctions and recent combined approaches to advance adaptive neural network training methods.

Contribution

It provides a unified terminology and formal framework for understanding and differentiating these interconnected learning paradigms, facilitating future research.

Findings

Organized various problem settings with consistent terminology

Highlighted recent algorithms combining meta-learning with online and continual learning

Clarified distinctions among different learning frameworks

Abstract

Over the past decade, deep neural networks have demonstrated significant success using the training scheme that involves mini-batch stochastic gradient descent on extensive datasets. Expanding upon this accomplishment, there has been a surge in research exploring the application of neural networks in other learning scenarios. One notable framework that has garnered significant attention is meta-learning. Often described as "learning to learn," meta-learning is a data-driven approach to optimize the learning algorithm. Other branches of interest are continual learning and online learning, both of which involve incrementally updating a model with streaming data. While these frameworks were initially developed independently, recent works have started investigating their combinations, proposing novel problem settings and learning algorithms. However, due to the elevated complexity and lack of unified terminology, discerning differences between the learning frameworks can be challenging even for experienced researchers. To facilitate a clear understanding, this paper provides a comprehensive survey that organizes various problem settings using consistent terminology and formal descriptions. By offering an overview of these learning paradigms, our work aims to foster further advancements in this promising area of research.