不断学习，快速概括：少样本学习的终身知识积累
Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning
摘要：
随着时间的推移不断扩展知识并利用它快速概括新任务的能力是人类语言智能的一个关键特征。追求快速泛化到新任务的现有模型（例如，然而，少样本学习方法）大多是在固定数据集上的Single Shot中训练的，不能动态地扩展它们的知识;而持续学习算法不是专门为快速泛化而设计的。我们提出了一个新的学习设置，持续学习的Few-Shot学习者（CLIF），以解决这两个学习设置在一个统一的设置的挑战。CLIF假设一个模型从一系列顺序到达的不同NLP任务中学习，积累知识以改进对新任务的泛化，同时保留先前学习的任务的性能。我们研究了泛化能力是如何影响的持续学习设置，评估了一些持续学习算法，并提出了一种新的正则化适配器生成方法。我们发现，灾难性遗忘对泛化能力的影响程度小于对看到的任务的性能，而持续学习算法仍然可以带来相当大的好处的泛化能力。
英文摘要：
The ability to continuously expand knowledge over time and utilize it to rapidly generalize to new tasks is a key feature of human linguistic intelligence. Existing models that pursue rapid generalization to new tasks (e.g., few-shot learning methods), however, are mostly trained in a single shot on fixed datasets, unable to dynamically expand their knowledge; while continual learning algorithms are not specifically designed for rapid generalization. We present a new learning setup, Continual Learning of Few-Shot Learners (CLIF), to address the challenges of both learning settings in a unified setup. CLIF assumes a model learns from a sequence of diverse NLP tasks arriving sequentially, accumulating knowledge for improved generalization to new tasks, while also retaining performance on the tasks learned earlier. We examine how the generalization ability is affected in the continual learning setup, evaluate a number of continual learning algorithms, and propose a novel regularized adapter generation approach. We find that catastrophic forgetting affects generalization ability to a less degree than performance on seen tasks; while continual learning algorithms can still bring considerable benefit to the generalization ability.
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。
