On Episodes, Prototypical Networks, and Few-shot Learning
This work addresses the efficiency and complexity of training for researchers and practitioners working on few-shot learning, offering a simpler and more effective approach for a class of methods.
This paper investigates the necessity of episodic learning in few-shot learning methods that use non-parametric approaches. It demonstrates that episodic learning is not only unnecessary but also data-inefficient for methods like Matching and Prototypical Networks, and their non-episodic counterparts achieve improved performance across multiple few-shot classification datasets.
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.