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}.

翻译：现有持续学习方法在训练过程中需要大量样本。由于过拟合问题，此类方法在许多样本受限的真实世界问题中不实用。本文提出一种称为FLat-tO-WidE AppRoach (FLOWER)的小样本持续学习方法，通过平坦到宽泛的学习过程寻找平坦宽泛极小值，以解决灾难性遗忘问题。数据稀缺问题通过数据增强方法克服，该方法利用球生成器概念将采样空间限制在最小包围球内。数值实验表明，FLOWER在小规模基础任务上相较于现有方法取得了显著性能提升。为便于进一步研究，FLOWER的源代码、对比算法及实验日志已公开于\url{https://github.com/anwarmaxsum/FLOWER}。