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›Deep learning›Variational Autoencoder
Machine learning

Variational Autoencoder

Variational Autoencoder (VAE) · Also known as: Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model

The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning.

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.

Variational Autoencoder
AutoencoderDiffusion ModelGenerative Adversarial N…Principal Component Anal…Score-Based Generative M…Autoencoder Anomaly Dete…Bayesian Gaussian Mixtur…Bayesian single-cell RNA…Domain-adaptive variatio…Explainable GAN

+26 more

When to use it

A good fit when you have at least about 200 continuous-valued observations and want to learn a smooth latent representation for generating new data, detecting anomalies, or compressing high-dimensional inputs, and a GPU is available for training. The model assumes a continuous latent variable and is trained by jointly optimising reconstruction loss and the KL divergence. Below about 200 samples the latent distribution cannot be learned meaningfully and a simpler method such as PCA is preferable; below about 50 it fails entirely.

Strengths & limitations

Strengths
  • Learns a smooth, continuous latent space that can be sampled to generate genuinely new examples.
  • Provides a principled probabilistic framework, optimising a single objective (the evidence lower bound).
  • Useful beyond generation — for anomaly detection, feature learning, and nonlinear dimensionality reduction.
  • Does not require normally distributed inputs and works with continuous data of high dimension.
  • The reparameterisation trick makes the whole model trainable end to end by gradient descent.
Limitations
  • Needs a reasonably large sample (about 200+) and typically a GPU to train effectively.
  • Samples can look blurry compared with adversarial or diffusion-based generators.
  • On small datasets the latent distribution is not learned meaningfully, so PCA is the safer choice.
  • Balancing the reconstruction and KL terms is delicate; the KL term can collapse and be ignored.

Frequently asked

How is a VAE different from a plain autoencoder?

A plain autoencoder maps each input to a single latent code optimised only for reconstruction. A VAE encodes each input as a probability distribution and adds a KL term that keeps that distribution close to a prior, which yields a smooth latent space you can sample from to generate new data.

What is the reparameterisation trick?

It rewrites a latent sample as the encoded mean plus the standard deviation times standard Gaussian noise. By moving the randomness into an external noise term, gradients can pass through the sampling step so the encoder and decoder can be trained together by backpropagation.

How much data and what hardware do I need?

At least about 200 continuous observations are recommended, and a GPU is advised for training. Below 200 the latent distribution is not learned meaningfully and PCA is preferable; below about 50 the VAE fails entirely.

What is beta-VAE?

beta-VAE, proposed by Higgins and colleagues in 2017, multiplies the KL term by a coefficient (beta). A larger beta pressures the latent dimensions to capture more independent, disentangled factors of variation, at some cost to reconstruction fidelity.

Sources

  1. Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR). link ↗
  2. Higgins, I. et al. (2017). beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. International Conference on Learning Representations (ICLR). link ↗

How to cite this page

ScholarGate. (2026, June 1). Variational Autoencoder (VAE). ScholarGate. https://scholargate.app/en/deep-learning/variational-autoencoder

Related methods

AutoencoderDiffusion ModelGenerative Adversarial NetworkPrincipal Component AnalysisScore-Based Generative Model

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.

  • AutoencoderDeep learning↔ compare
  • Diffusion ModelDeep learning↔ compare
  • Generative Adversarial NetworkDeep learning↔ compare
  • Principal Component AnalysisMachine learning↔ compare
  • Score-Based Generative ModelDeep learning↔ compare
Compare side by side →

Referenced by

AutoencoderAutoencoder Anomaly DetectionBayesian Gaussian Mixture ModelBayesian single-cell RNA-seq analysisDiffusion ModelDomain-adaptive variational autoencoderExplainable GANExplainable Gaussian Mixture ModelExplainable Variational AutoencoderFine-Tuned Variational AutoencoderGenerative Adversarial NetworkGPT Fine-TuningLoRA and PEFTMultilingual variational autoencoderMultimodal Variational AutoencoderNeural Style TransferNormalizing FlowsRestricted Boltzmann MachineScore-Based Generative ModelSelf-supervised Autoencoder Anomaly DetectionSelf-supervised Diffusion ModelSelf-supervised Gaussian Mixture ModelSelf-supervised Gaussian ProcessSelf-supervised Variational AutoencoderSemi-supervised Diffusion ModelSemi-supervised GANSemi-supervised Gaussian Mixture ModelSemi-supervised LSTMSemi-supervised Variational AutoencoderTransfer learning GANTransfer learning variational autoencoderVision TransformerWeakly Supervised Diffusion ModelWeakly supervised GANWeakly Supervised Variational Autoencoder

Similar methods

Bayesian Autoencoder Anomaly DetectionExplainable Variational AutoencoderAutoencoderTransfer learning variational autoencoderFine-Tuned Variational AutoencoderSemi-supervised Variational AutoencoderSelf-supervised Variational AutoencoderWeakly Supervised Variational Autoencoder

Related reference concepts

Deep Generative ModelsVariational InferenceUnsupervised LearningLatent Variable and Mixture ModelsDimensionality ReductionSelf-Supervised and Representation Learning

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

ScholarGate — Variational Autoencoder (Variational Autoencoder (VAE)). Retrieved 2026-07-21 from https://scholargate.app/en/deep-learning/variational-autoencoder · Dataset: https://doi.org/10.5281/zenodo.20539026
Quick facts
Originator
Kingma, D. P. & Welling, M.
Year
2014
Type
Deep generative latent-variable model (encoder–decoder)
Task
Generative modelling, dimensionality reduction, anomaly detection
MinSample
200
Related methods
AutoencoderDiffusion ModelGenerative Adversarial NetworkPrincipal Component AnalysisScore-Based Generative Model
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