利用持续学习技术加速批量主动学习
Accelerating Batch Active Learning Using Continual Learning Techniques
AI总结：
针对主动学习每轮查询后需从头重训导致成本高的问题，提出结合回放式持续学习的持续主动学习范式，在多领域实验中实现3倍训练加速且性能无损。
摘要：
主动学习（Active Learning，AL）的一个核心问题是训练成本高昂，因为模型通常需要在每轮查询后从头重新训练。我们首先证明，采用热启动的神经网络标准主动学习方法不仅无法加速训练，而且在跨主动学习查询轮次进行微调时，也无法避免灾难性遗忘问题。随后我们开发了一类新技术来规避这一问题，核心思路是让后续训练向已标注的历史数据集偏移。我们通过结合现有的、以及全新开发的基于回放的持续学习（Continual Learning，CL）算法实现这一目标，这类算法能有效学习新数据同时不遗忘旧知识，尤其适用于数据分布不断变化的场景。我们将这一范式命名为持续主动学习（Continual Active Learning，CAL）。实验表明，借助多种采用模型蒸馏、并从历史数据中筛选兼具多样性和不确定性样本的回放策略，CAL实现了显著的训练加速。我们在自然语言、计算机视觉、医学影像、计算生物学等多个数据领域开展实验，各领域分别采用不同的神经网络架构和数据集规模。结果显示，CAL始终能将训练时间缩短3倍，同时保持模型性能不下降。
英文摘要：
A major problem with Active Learning (AL) is high training costs since models are typically retrained from scratch after every query round. We start by demonstrating that standard AL on neural networks with warm starting fails, both to accelerate training and to avoid catastrophic forgetting when using fine-tuning over AL query rounds. We then develop a new class of techniques, circumventing this problem, by biasing further training towards previously labeled sets. We accomplish this by employing existing, and developing novel, replay-based Continual Learning (CL) algorithms that are effective at quickly learning the new without forgetting the old, especially when data comes from an evolving distribution. We call this paradigm Continual Active Learning (CAL). We show CAL achieves significant speedups using a plethora of replay schemes that use model distillation and that select diverse, uncertain points from the history. We conduct experiments across many data domains, including natural language, vision, medical imaging, and computational biology, each with different neural architectures and dataset sizes. CAL consistently provides a 3x reduction in training time, while retaining performance.
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。
