CopulaGANGenerator<T>

Models & Types · AiDotNet.NeuralNetworks.SyntheticData

CopulaGAN generator for synthetic tabular data, combining Gaussian copula transformations with the CTGAN training pipeline for improved continuous column modeling.

Inheritance: NeuralNetworkBase<T> → NeuralSyntheticTabularGeneratorBase<T> → CopulaGANGenerator<T>

Implements: ISyntheticTabularGenerator<T>

For Beginners

CopulaGAN is CTGAN with an extra “normalizing” step:

**Training:**Generation:

If you provide custom layers in the architecture, those will be used directly for the generator network. If not, the network creates industry-standard CopulaGAN layers based on the original research paper specifications.

Example usage:

How It Works

CopulaGAN applies a two-stage preprocessing to continuous columns:

  1. Gaussian copula transform: CDF then quantile then standard normal
  2. VGM normalization: Standard CTGAN mode-specific normalization

This implementation follows the standard neural network architecture pattern with:

  • Proper inheritance from NeuralNetworkBase
  • Layer-based architecture using ILayer components
  • Engine-based tensor operations for CPU/GPU acceleration
  • Full autodiff and JIT compilation support

Reference: “Synthesizing Tabular Data using Copulas” (2020)

Constructors

Constructor Summary
CopulaGANGenerator() Initializes a new CopulaGAN generator with the specified architecture.
CopulaGANGenerator(NeuralNetworkArchitecture<T> architecture, CopulaGANOptions<T> options, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer, ILossFunction<T> lossFunction)

Properties

Property Summary
CopulaGANOptions<T> Options { get; } Gets the CopulaGAN-specific options.
IReadOnlyList<ColumnMetadata> Columns { get; }
bool IsFitted { get; set; }

Methods

Method Summary
Dictionary<string, T> GetFeatureImportance()
Matrix<T> Generate(int numSamples, Vector<T> conditionColumn, Vector<T> conditionValue) Generates new synthetic tabular data rows.
ModelMetadata<T> GetModelMetadata()
Task FitAsync(Matrix<T> data, IReadOnlyList<ColumnMetadata> columns, int? epochs, CancellationToken ct)
void Fit(Matrix<T> data, IReadOnlyList<ColumnMetadata> columns, int? epochs) Fits the CopulaGAN generator to the provided real tabular data.