Skip to contentScholarGate
LibraryBookshelfDeskReview StudioAssistant
Sign in
On this page
IntuitionHow it worksWhen to use itStrengths & limitationsCommon pitfallsApplicationsFrequently asked🔒 Read the full methodSourcesRelated methods
Cite this pageSpotted an issue on this page? Report or suggest a fix →
Home›Machine learning›Few-shot Learning
Machine learningMachine learning

Few-shot Learning

Few-shot Learning (Meta-learning with Limited Labeled Examples) · Also known as: FSL, low-shot learning, k-shot learning, meta-learning for few examples

Few-shot learning is a machine learning paradigm that trains models to recognize new classes or solve new tasks from only a handful of labeled examples — typically one to five — by leveraging prior knowledge acquired from a large, related training distribution. It is especially relevant in domains where labeling is expensive, scarce, or structurally limited.

ScholarGate
  1. Machine learning
  2. v1
  3. 2 Sources
  4. PUBLISHED
Cite this page →
Tools & resources
Download slides
Learn & explore

Read the full method

Members only

Sign in with a free account to read this section.

Sign in

Method map

The neighbourhood of related methods — select a node to explore.

Few-shot Learning
Metric LearningSelf-supervised LearningSemi-supervised LearningTransfer LearningActive Learning Self-sup…Bayesian Active LearningBayesian Few-Shot Learni…Bayesian Metric LearningBayesian Semi-supervised…Bayesian Transfer Learni…

+17 more

When to use it

Use few-shot learning when labeled data for a target task is genuinely scarce — fewer than roughly 10 to 20 examples per class — but a large related dataset is available for pre-training or meta-training. Typical use cases include rare-disease classification, endangered-species recognition, low-resource language tasks, and personalized recommendation with cold-start users. Do not use it as a substitute for collecting more labeled data when labeling is feasible; with sufficient labels, fully supervised or fine-tuned transfer learning will nearly always outperform few-shot methods. Also avoid it if the meta-training distribution is very different from the target domain, as this invalidates the learned prior.

Strengths & limitations

Strengths
  • Enables practical learning from one to five labeled examples per class, dramatically reducing annotation cost.
  • Episodic training explicitly prepares the model for the low-data deployment scenario it will face.
  • Metric-based variants (Prototypical Networks, Matching Networks) are computationally lightweight at inference — no gradient steps required.
  • Widely applicable across vision, NLP, audio, and structured data tasks.
  • Naturally integrates with large pre-trained models, allowing powerful priors to be exploited without full fine-tuning.
Limitations
  • Requires a large, diverse meta-training set; performance degrades sharply when the meta-training and target distributions diverge significantly.
  • Optimization-based methods (e.g., MAML) are computationally intensive during meta-training due to second-order gradients.
  • Benchmark accuracy on standard datasets (miniImageNet, Omniglot) can overstate real-world performance if the test domain differs.
  • Choosing the right architecture, embedding backbone, and episode sampling strategy involves non-trivial hyperparameter decisions.
  • With more than about 20 labeled examples per class, standard transfer learning or fine-tuning typically offers better accuracy with less complexity.

Frequently asked

What is the difference between few-shot learning and transfer learning?

Transfer learning fine-tunes a pre-trained model on a new task and typically benefits from tens to thousands of labeled examples. Few-shot learning is specifically designed to adapt with only one to five examples per class, using episodic meta-training so the model learns how to generalize quickly rather than how to fit a specific domain.

What does k-shot n-way mean?

It describes the episode structure: n-way means n novel classes are presented simultaneously, and k-shot means k labeled examples are provided per class. A 5-way 1-shot task asks the model to classify query images into one of five categories given only a single labeled example for each.

Do I need a GPU to run few-shot learning?

Meta-training — especially optimization-based methods like MAML — requires substantial compute and is typically done on GPUs. However, metric-based inference (comparing query embeddings to support prototypes) is cheap and can run on CPU in production once the backbone is pre-trained.

How many meta-training tasks do I need?

This depends on diversity rather than absolute count. A few thousand episodically sampled tasks from a varied class pool is a common baseline. What matters most is that the meta-training classes are numerous and diverse enough to generalize to unseen target classes.

Is few-shot learning the same as zero-shot learning?

No. Zero-shot learning requires no labeled examples from novel classes at test time, relying entirely on semantic class descriptors or attributes. Few-shot learning always provides at least one labeled example per novel class in the support set.

Sources

  1. Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., & Kavukcuoglu, K. (2016). Matching Networks for One Shot Learning. Advances in Neural Information Processing Systems (NeurIPS), 29. link ↗
  2. Finn, C., Abbeel, P., & Levine, S. (2017). Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks. Proceedings of the 34th International Conference on Machine Learning (ICML), PMLR 70:1126–1135. link ↗

How to cite this page

ScholarGate. (2026, June 3). Few-shot Learning (Meta-learning with Limited Labeled Examples). ScholarGate. https://scholargate.app/en/machine-learning/few-shot-learning

Related methods

Metric LearningSelf-supervised LearningSemi-supervised LearningTransfer Learning

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

  • Metric LearningMachine learning↔ compare
  • Self-supervised LearningMachine learning↔ compare
  • Semi-supervised LearningMachine learning↔ compare
  • Transfer LearningMachine learning↔ compare
Compare side by side →

Referenced by

Active Learning Self-supervised LearningBayesian Active LearningBayesian Few-Shot LearningBayesian Metric LearningBayesian Semi-supervised LearningBayesian Transfer LearningEnsemble Few-shot learningEnsemble Metric LearningEnsemble Transfer LearningMetric LearningOnline Active learningOnline Few-shot LearningOnline LearningOnline Transfer learningRegularized Few-Shot LearningRegularized Transfer LearningRobust Active LearningRobust Metric LearningSelf-supervised Federated learningSelf-supervised LearningSelf-supervised named entity recognitionSelf-supervised Transfer learningSemi-supervised Federated learningSemi-supervised Few-shot LearningSemi-supervised LearningSemi-supervised Metric LearningTransfer Learning

Similar methods

Bayesian Few-Shot LearningOnline Few-shot LearningRegularized Few-Shot LearningSelf-supervised Few-shot LearningSemi-supervised Few-shot LearningFew-Shot Text ClassificationFew-Shot Object DetectionEnsemble Few-shot learning

Related reference concepts

Supervised LearningMachine LearningSelf-Supervised and Representation LearningHyperparameter OptimizationVC Dimension and CapacityUnsupervised Learning

Spotted an issue on this page? Report or suggest a fix →

ScholarGate — Few-shot Learning (Few-shot Learning (Meta-learning with Limited Labeled Examples)). Retrieved 2026-07-21 from https://scholargate.app/en/machine-learning/few-shot-learning · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Lake, B. M.; Vinyals, O.; Finn, C. et al.
Year
2011–2017
Type
Meta-learning / low-data learning paradigm
DataType
Labeled images, text, or structured data with very few examples per class
Subfamily
Machine learning
Related methods
Metric LearningSelf-supervised LearningSemi-supervised LearningTransfer Learning
ScholarGate

A content-first reference library for research methods — what each one is, how it works, and where it comes from.

Open data (CC-BY)

Explore

  • Library
  • Search the library…
  • Browse by field
  • Fields
  • Journey
  • Compare
  • Which method?

Reference

  • Subjects
  • Atlas
  • Glossary
  • Methodology
  • Philosophy

Your tools

  • Bookshelf
  • Desk
  • Chat

Company

  • About
  • Pricing
  • Contact
  • Suggest a method

Entries are compiled from published sources for reference. Verifying the accuracy and suitability of any information for your own use remains your responsibility.

© 2026 ScholarGate · A research-method reference library
  • Privacy
  • Cookies
  • Terms
  • Delete account