用少量样本评估持续学习，发现新方法能更好适应未来任务。
Re-Evaluating Continual Learning with Few-Shot Adaptation
- 用少量样本测试模型在旧任务上的记忆和新任务上的适应能力。
- 引入每样本可塑性指标，揭示模型对后续任务的预判学习效果。
- 适合研究持续学习、元学习与快速适应的学者参考。
持续学习旨在提升模型在连续任务序列中保持稳定性与可塑性的能力。传统评估以零样本性能衡量稳定性（即遗忘程度），以最新任务性能衡量可塑性，但零样本评估要求模型完美回忆多任务知识，无法全面反映模型保留信息或快速适应新信息的能力。本文提出少样本评估范式，对图像分类任务序列进行细致分析，发现该方法能揭示主流持续学习策略的新见解。通过引入新的‘每样本可塑性’指标，我们表明：通过元学习未来短序列任务来引入‘远见’，可使模型在任务序列上产生学习如何学习的行为。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。