AutoIntOptions<T>

Options & Configuration · AiDotNet.Models.Options

Configuration options for AutoInt (Automatic Feature Interaction Learning).

Inheritance: ModelOptions → NeuralNetworkOptions → ModelHyperparameterOptions → FinancialNeuralNetworkOptions → RiskModelOptions<T> → AutoIntOptions<T>

For Beginners

AutoInt is designed to find interactions between features:

  • Feature embeddings: Each feature is converted to a vector
  • Self-attention layers: Features attend to each other to learn interactions
  • Explicit interactions: The model learns “feature A combined with feature B”

Example use case: In click-through rate prediction, “age + product_category” might have a strong interaction that AutoInt can automatically discover.

Example:

How It Works

AutoInt uses multi-head self-attention to automatically learn high-order feature interactions without manual feature engineering.

Reference: “AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks” (2018)

Constructors

Constructor Summary
AutoIntOptions()

Properties

Property Summary
IActivationFunction<T> HiddenActivation { get; set; } Gets or sets the hidden layer activation function.
IVectorActivationFunction<T> HiddenVectorActivation { get; set; } Gets or sets the hidden layer vector activation function (alternative to scalar activation).
bool UseResidual { get; set; } Gets or sets whether to use residual connections.
double DropoutRate { get; set; } Gets or sets the dropout rate.
double EmbeddingInitScale { get; set; } Gets or sets the initialization scale for embeddings.
int AttentionDimension { get; set; } Gets or sets the attention dimension per head.
int EmbeddingDimension { get; set; } Gets or sets the embedding dimension for features.
int NumHeads { get; set; } Gets or sets the number of attention heads per layer.
int NumLayers { get; set; } Gets or sets the number of interacting (self-attention) layers.
int[] CategoricalCardinalities { get; set; } Gets or sets the cardinalities of categorical features.
int[] MLPHiddenDimensions { get; set; } Gets or sets the hidden dimensions for the MLP output layer.