面向少样本持续主动学习的学会学习
Learning to Learn for Few-shot Continual Active Learning
AI总结：
针对标注数据不足且预算有限的少样本持续主动学习问题，提出Meta-Continual Active Learning方法，结合元学习、经验回放与文本增强解决灾难性遗忘并确保泛化能力。
摘要：
持续学习致力于在解决先前已见任务时保持稳定性，同时在新领域展现可塑性。近期持续学习的进展主要局限于监督学习设置，尤其是在NLP领域。在本研究中，我们考虑一种少样本持续主动学习设置，其中标注数据不足，而未标注数据丰富但标注预算有限。我们利用元学习并提出一种名为Meta-Continual Active Learning的方法。该方法从无标注数据池中顺序查询最具信息量的样本进行标注，以提升任务特定性能，并通过元目标解决持续学习问题。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。我们进一步引入文本增强，以避免经验回放和样本查询导致的记忆过拟合，从而确保泛化能力。我们在来自不同领域的基准文本分类数据集上进行了广泛实验，以验证Meta-Continual Active Learning的可行性和有效性。我们还分析了不同主动学习策略对各种元持续学习模型的影响。实验结果表明，在样本选择中引入随机性是维持元持续学习框架泛化能力的最佳默认策略。
英文摘要：
Continual learning strives to ensure stability in solving previously seen tasks while demonstrating plasticity in a novel domain. Recent advances in continual learning are mostly confined to a supervised learning setting, especially in NLP domain. In this work, we consider a few-shot continual active learning setting where labeled data are inadequate, and unlabeled data are abundant but with a limited annotation budget. We exploit meta-learning and propose a method, called Meta-Continual Active Learning. This method sequentially queries the most informative examples from a pool of unlabeled data for annotation to enhance task-specific performance and tackle continual learning problems through meta-objective. Specifically, we employ meta-learning and experience replay to address inter-task confusion and catastrophic forgetting. We further incorporate textual augmentations to avoid memory over-fitting caused by experience replay and sample queries, thereby ensuring generalization. We conduct extensive experiments on benchmark text classification datasets from diverse domains to validate the feasibility and effectiveness of meta-continual active learning. We also analyze the impact of different active learning strategies on various meta continual learning models. The experimental results demonstrate that introducing randomness into sample selection is the best default strategy for maintaining generalization in meta-continual learning framework.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
