Skip to content

Deep Generative Model

Definition
AI-generated

A deep generative model is a neural network that defines or approximates a distribution over high-dimensional data—images, sequences, tabular features, or count matrices—using architectures such as variational autoencoders, generative adversarial networks, normalizing flows, autoregressive models, or diffusion frameworks.

Topics
LLM and Agents
Related
Autoencoder Disentangled Representation Learning Foundation Model

Why it matters in GWAS

Generative models underpin reference mapping, batch harmonization, synthetic controls, and phenotype or molecular imputation in resource-scarce settings. When linked to genetic data, their latent spaces and simulators must be audited for ancestry, batch, and selection bias so downstream association or polygenic analyses are not silently distorted.

Example usage

"The methods use Deep Generative Model to improve representation learning before downstream association tasks."

Autoencoder Disentangled Representation Learning Foundation Model Neural Network Variational Autoencoder (VAE) In Silico Perturbation Prediction Single-Cell Foundation Model
Related-term network

Click any node to open that term page.

Node order. The current term is first. Next come every page linked from Related terms, in the same top-to-bottom order as that list. Then new terms appear in two-hop layers: for each of those direct neighbors (in that same order), their related terms are appended if not already listed. A third pass does the same for two-hop nodes. The walk stops when a fixed maximum number of nodes is reached.

References

  • Goodfellow I, et al. (2014). Generative adversarial nets. NeurIPS.
  • Kingma DP, Welling M. (2014). Auto-encoding variational Bayes. ICLR.
  • Bond-Taylor S, et al. (2022). Deep generative modelling: a comparative review of VAEs, GANs, normalizing flows, energy-based and autoregressive models. IEEE TPAMI.
← Decoy sequence Deep Learning →

Last updated (UTC · Git history)