Few-Shot Continual Learning via Flat-to-Wide Approaches
This addresses the impracticality of existing continual learning methods that require many samples, offering a solution for real-world problems with data scarcity, though it appears incremental in its approach.
The paper tackles the problem of catastrophic forgetting in continual learning with limited data by proposing FLOWER, a few-shot continual learning approach that finds flat-wide minima and uses data augmentation with a ball generator. The method achieves significantly improved performance over prior arts, especially in small base tasks.
Existing approaches on continual learning call for a lot of samples in their training processes. Such approaches are impractical for many real-world problems having limited samples because of the overfitting problem. This paper proposes a few-shot continual learning approach, termed FLat-tO-WidE AppRoach (FLOWER), where a flat-to-wide learning process finding the flat-wide minima is proposed to address the catastrophic forgetting problem. The issue of data scarcity is overcome with a data augmentation approach making use of a ball generator concept to restrict the sampling space into the smallest enclosing ball. Our numerical studies demonstrate the advantage of FLOWER achieving significantly improved performances over prior arts notably in the small base tasks. For further study, source codes of FLOWER, competitor algorithms and experimental logs are shared publicly in \url{https://github.com/anwarmaxsum/FLOWER}.