Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in CL are mostly confined to a supervised learning setting, especially in NLP domain. In this work, we consider a few-shot continual active learning (CAL) setting where labeled data are inadequate, and unlabeled data are abundant but with a limited annotation budget. We propose a simple but efficient method, called Meta-Continual Active Learning. Specifically, we employ meta-learning and experience replay to address inter-task confusion and catastrophic forgetting. We further incorporate textual augmentations to ensure generalization. We conduct extensive experiments on benchmark text classification datasets to validate the effectiveness of the proposed method and analyze the effect of different active learning strategies in few-shot CAL setting. Our experimental results demonstrate that random sampling is the best default strategy for active learning and memory sample selection to solve few-shot CAL problems.

翻译：持续学习致力于在解决已见任务时保持稳定性，同时在处理新领域时展现塑性。当前的持续学习研究多局限于监督学习场景，尤其在自然语言处理领域。本研究考虑了一种小样本持续主动学习场景，其中标注数据不足，未标注数据丰富但标注预算有限。我们提出了一种简单而高效的方法——元持续主动学习。具体而言，我们采用元学习和经验回放来解决任务间混淆和灾难性遗忘问题，并进一步引入文本增强以保证泛化能力。我们在基准文本分类数据集上进行了广泛实验，验证了所提方法的有效性，并分析了不同主动学习策略在小样本持续主动学习场景中的效果。实验结果表明，随机采样是解决小样本持续主动学习问题的最佳默认主动学习及记忆样本选择策略。