重新评估带少样本适应的持续学习
Re-Evaluating Continual Learning with Few-Shot Adaptation
AI总结：
本文提出用少样本评估替代零样本评估来更全面衡量持续学习系统的稳定性和可塑性，并通过新指标“每样本可塑性”发现元学习未来任务序列能诱导学习到学习行为。
摘要：
持续学习方法旨在最大化在任务序列上训练的机器学习模型的稳定性和可塑性。稳定性的标准度量（即遗忘）是模型在先前学习任务上的零样本性能，而可塑性则是在最近学习任务上的性能。然而，零样本评估并未完全衡量模型或方法保留已学信息或快速适应新信息的能力，因为它需要在多个任务上完美回忆。在本文中，我们提出少样本评估作为对持续学习系统稳定性和可塑性的更全面评估。我们对持续图像分类的任务序列进行了细粒度评估，发现这一范式为流行持续学习策略的性能提供了新颖的见解。通过使用新指标——每样本可塑性——进行少样本评估，我们展示了通过元学习未来任务的短序列向持续学习方法添加“前瞻性”会在任务序列上诱导学习到学习的行为。
英文摘要：
Continual learning methods aim to maximize the stability and plasticity of machine learning models that are trained on a sequence of tasks. The standard measure of stability (i.e., forgetting) is the 0-shot performance of a model on previously learned tasks, and plasticity, the performance on the most recently learned task. However, 0-shot evaluation does not fully measure a model or method's ability to retain learned information or adapt quickly to new information, as it requires perfect recall across multiple tasks. In this paper, we propose few-shot evaluation as a more comprehensive assessment of the stability and plasticity of a continual learning system. We conduct a fine-grained assessment on task sequences for continual image classification and find that this paradigm produces novel insights into the performance of popular continual learning strategies. Through few-shot evaluation with a novel metric -- per-shot plasticity -- we show that adding `foresight' to continual learning methods via the meta-learning of a short sequence of future tasks induces learning-to-learn behavior over the task sequence.
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。
