GraphNeuralNetworkOptions

Options & Configuration · AiDotNet.NeuralNetworks.Options

Configuration options for the GraphNeuralNetwork.

Inheritance: ModelOptions → NeuralNetworkOptions → GraphNeuralNetworkOptions

Constructors

Constructor Summary
GraphNeuralNetworkOptions() Initializes a new instance with default values.
GraphNeuralNetworkOptions(GraphNeuralNetworkOptions other) Initializes a new instance by copying every property from another instance.

Properties

Property Summary
bool UseAuxiliaryLoss { get; set; } Gets or sets whether the optional graph-smoothness loss is enabled.
bool UseBias { get; set; } Gets or sets whether graph-convolutional layers include trainable biases.
double AuxiliaryLossWeight { get; set; } Gets or sets the optional graph-smoothness loss weight.
double DropoutRate { get; set; } Gets or sets the dropout probability.
double L2Regularization { get; set; } Gets or sets the L2 regularization strength.
double LearningRate { get; set; } Gets or sets the Adam learning rate.
int HiddenSize { get; set; } Gets or sets the hidden feature width.
int NodeFeatureSize { get; set; } Gets or sets the number of input features per node.
int NumClasses { get; set; } Gets or sets the number of output classes.
int NumLayers { get; set; } Gets or sets the total number of graph-convolutional layers.