# On Episodes, Prototypical Networks, and Few-shot Learning

arXiv: https://arxiv.org/abs/2012.09831 · HTML: https://mlsanity.com/paper/2012.09831/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2020.

## Built on by (most cited first, 30 of 46)

- [Advances and Challenges in Meta-Learning: A Technical Review](https://mlsanity.com/paper/2307.04722/) (2023)
- [Spatio-temporal Relation Modeling for Few-shot Action Recognition](https://mlsanity.com/paper/2112.05132/) (2021)
- [Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later](https://mlsanity.com/paper/2407.03257/) (2024)
- [ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition](https://mlsanity.com/paper/2104.03841/) (2021)
- [Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Survey](https://mlsanity.com/paper/2211.04324/) (2022)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models](https://mlsanity.com/paper/2305.02279/) (2023)
- [Self-Supervision Can Be a Good Few-Shot Learner](https://mlsanity.com/paper/2207.09176/) (2022)
- [A Closer Look at Prototype Classifier for Few-shot Image Classification](https://mlsanity.com/paper/2110.05076/) (2021)
- [Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning](https://mlsanity.com/paper/2306.10511/) (2023)
- [Sparse Spatial Transformers for Few-Shot Learning](https://mlsanity.com/paper/2109.12932/) (2021)
- [Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants](https://mlsanity.com/paper/2308.01746/) (2023)
- [Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification](https://mlsanity.com/paper/2206.08138/) (2022)
- [Bridging Few-Shot Learning and Adaptation: New Challenges of Support-Query Shift](https://mlsanity.com/paper/2105.11804/) (2021)
- [Uniform Sampling over Episode Difficulty](https://mlsanity.com/paper/2108.01662/) (2021)
- [Learning Meta Representations of One-shot Relations for Temporal Knowledge Graph Link Prediction](https://mlsanity.com/paper/2205.10621/) (2022)
- [Towards Incremental Learning in Large Language Models: A Critical Review](https://mlsanity.com/paper/2404.18311/) (2024)
- [INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomy](https://mlsanity.com/paper/2502.01896/) (2025)
- [Texture based Prototypical Network for Few-Shot Semantic Segmentation of Forest Cover: Generalizing for Different Geographical Regions](https://mlsanity.com/paper/2203.15687/) (2022)
- [Adaptive Prototypical Networks](https://mlsanity.com/paper/2211.12479/) (2022)
- [A Flexible Nadaraya-Watson Head Can Offer Explainable and Calibrated Classification](https://mlsanity.com/paper/2212.03411/) (2022)
- [Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies](https://mlsanity.com/paper/2310.10500/) (2023)
- [Towards Novel Malicious Packet Recognition: A Few-Shot Learning Approach](https://mlsanity.com/paper/2409.11254/) (2024)
- [Modularity in Deep Learning: A Survey](https://mlsanity.com/paper/2310.01154/) (2023)
- [Expert-Guided Explainable Few-Shot Learning with Active Sample Selection for Medical Image Analysis](https://mlsanity.com/paper/2601.02409/) (2026)
- [Unsupervised Few-shot Learning via Deep Laplacian Eigenmaps](https://mlsanity.com/paper/2210.03595/) (2022)
- [Few-shot Classification with Hypersphere Modeling of Prototypes](https://mlsanity.com/paper/2211.05319/) (2022)
- [Towards Generative Class Prompt Learning for Fine-grained Visual Recognition](https://mlsanity.com/paper/2409.01835/) (2024)
- [Packet Inspection Transformer: A Self-Supervised Journey to Unseen Malware Detection with Few Samples](https://mlsanity.com/paper/2409.18219/) (2024)
- [Meta-Transfer Derm-Diagnosis: Exploring Few-Shot Learning and Transfer Learning for Skin Disease Classification in Long-Tail Distribution](https://mlsanity.com/paper/2404.16814/) (2024)

## Abstract (arXiv)

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.