论文标题
在情节，典型网络和少数学习
On Episodes, Prototypical Networks, and Few-shot Learning
论文作者
论文摘要
情节学习是对几次学习感兴趣的研究人员和从业者的流行实践。它包括在一系列学习问题（或情节）中组织培训，每个培训分为一个小的培训和验证子集，以模仿评估过程中遇到的情况。但这总是必要的吗？在本文中，我们研究了情节学习在情节级别上使用非参数方法（例如最近的邻居）的方法的实用性。对于这些方法，我们不仅显示了无需通过情节学习施加的约束，而且实际上它们会导致一种利用培训批次的数据信息。我们通过匹配和典型网络进行了广泛的消融实验，这是在情节级别上使用非参数方法的两种最受欢迎的方法。他们的“非剧本”对应物更简单，具有较少的超参数，并在多个弹出的分类数据集中提高其性能。
Episodic learning is a popular practice among researchers and practitioners interested in few-shot learning. It consists of organising training in a series of learning problems (or episodes), each divided into a small training and validation subset to mimic the circumstances encountered during evaluation. But is this always necessary? In this paper, we investigate the usefulness of episodic learning in methods which use nonparametric approaches, such as nearest neighbours, at the level of the episode. For these methods, we not only show how the constraints imposed by episodic learning are not necessary, but that they in fact lead to a data-inefficient way of exploiting training batches. We conduct a wide range of ablative experiments with Matching and Prototypical Networks, two of the most popular methods that use nonparametric approaches at the level of the episode. Their "non-episodic" counterparts are considerably simpler, have less hyperparameters, and improve their performance in multiple few-shot classification datasets.
