Regularization Shortcomings for Continual Learning
This work addresses the problem of catastrophic forgetting in continual learning for researchers, highlighting a critical limitation in existing methods.
The paper demonstrates that regularization-based approaches in continual learning fail to discriminate between classes from different tasks in class-incremental scenarios, supported by theoretical reasoning and experiments, with implications for multi-task reinforcement learning and pre-trained models.
In most machine learning algorithms, training data is assumed to be independent and identically distributed (iid). When it is not the case, the algorithm's performances are challenged, leading to the famous phenomenon of catastrophic forgetting. Algorithms dealing with it are gathered in the Continual Learning research field. In this paper, we study the regularization based approaches to continual learning and show that those approaches can not learn to discriminate classes from different tasks in an elemental continual benchmark: the class-incremental scenario. We make theoretical reasoning to prove this shortcoming and illustrate it with examples and experiments. Moreover, we show that it can have some important consequences on continual multi-tasks reinforcement learning or in pre-trained models used for continual learning. We believe that highlighting and understanding the shortcomings of regularization strategies will help us to use them more efficiently.