GOGGLEGenerator<T>
Models & Types · AiDotNet.NeuralNetworks.SyntheticData
GOGGLE generator that learns feature dependency structure via a graph neural network combined with a VAE framework for high-quality synthetic tabular data generation.
Inheritance: NeuralNetworkBase<T> → NeuralSyntheticTabularGeneratorBase<T> → GOGGLEGenerator<T>
Implements: ISyntheticTabularGenerator<T>
For Beginners
GOGGLE figures out which features relate to each other:
- Learns a “graph” where connected features influence each other
- Uses this graph to share information between related features
- Generates new data where these relationships are preserved
If you provide custom layers in the architecture, those will be used for the decoder (MLP) network. If not, the network creates standard decoder layers based on the original paper specifications.
Example usage:
How It Works
GOGGLE operates in three stages:
The adjacency matrix A is learned end-to-end alongside the encoder/decoder. Regularization encourages A to be sparse and approximately acyclic (DAG-like).
This implementation follows the standard neural network architecture pattern with:
- Proper inheritance from NeuralNetworkBase
- Layer-based architecture using ILayer components
- Full forward/backward/update lifecycle
Reference: “GOGGLE: Generative Modelling for Tabular Data by Learning Relational Structure” (Liu et al., ICLR 2023)
Constructors
| Constructor | Summary |
|---|---|
GOGGLEGenerator() |
Initializes a new GOGGLE generator with the specified architecture. |
GOGGLEGenerator(NeuralNetworkArchitecture<T> architecture, GOGGLEOptions<T> options, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer, ILossFunction<T> lossFunction) |
Properties
| Property | Summary |
|---|---|
GOGGLEOptions<T> GoggleOptions { get; } |
Gets the GOGGLE-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) |
|
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) |