Three types of incremental learning

• Published in: Nature machine intelligence Vol. 4; no. 12; pp. 1185 - 1197
• Main Authors: van de Ven, Gido M., Tuytelaars, Tinne, Tolias, Andreas S.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 01.12.2022; Nature Publishing Group
• Subjects: 631/378/116/2396; 639/705/117; 639/705/794; Algorithms; Artificial intelligence; Artificial neural networks; Deep learning; Domains; Engineering; Initiatives; Machine learning; Neural networks; Computer science; Learning algorithms; Software
• ISSN: 2522-5839; 2522-5839
• DOI: 10.1038/s42256-022-00568-3

Incrementally learning new information from a non-stationary stream of data, referred to as ‘continual learning’, is a key feature of natural intelligence, but a challenging problem for deep neural networks. In recent years, numerous deep learning methods for continual learning have been proposed, but comparing their performances is difficult due to the lack of a common framework. To help address this, we describe three fundamental types, or ‘scenarios’, of continual learning: task-incremental, domain-incremental and class-incremental learning. Each of these scenarios has its own set of challenges. To illustrate this, we provide a comprehensive empirical comparison of currently used continual learning strategies, by performing the Split MNIST and Split CIFAR-100 protocols according to each scenario. We demonstrate substantial differences between the three scenarios in terms of difficulty and in terms of the effectiveness of different strategies. The proposed categorization aims to structure the continual learning field, by forming a key foundation for clearly defining benchmark problems. A challenge for any machine learning system is to continually adapt to new data. While methods to address this issue are developed, their performance is hard to compare. A new framework to facilitate benchmarking divides approaches into three categories, defined by whether models need to adapt to new tasks, domains or classes.