ETPNOptions<T, TInput, TOutput>

Options & Configuration ยท AiDotNet.MetaLearning.Options

Configuration options for ETPN (Embedding-Transformed Prototypical Networks).

Inheritance: ModelOptions โ†’ ETPNOptions<T, TInput, TOutput>

Implements: IMetaLearnerOptions<T>

How It Works

ETPN learns a task-specific embedding transformation applied transductively using both support and query gradient information. The transformation adapts the parameter space to be more discriminative for the specific task at hand.

Constructors

Constructor Summary
ETPNOptions(IFullModel<T, TInput, TOutput> metaModel) Creates options for meta-learning metaModel, with the default settings.

Properties

Property Summary
IEpisodicDataLoader<T, TInput, TOutput> DataLoader { get; set; } Episodic data loader that supplies the meta-training tasks; null when tasks are passed to training directly.
IFullModel<T, TInput, TOutput> MetaModel { get; set; } The model whose parameters the meta-learner trains to adapt quickly to new tasks.
IGradientBasedOptimizer<T, TInput, TOutput> InnerOptimizer { get; set; } Optimizer for task adaptation.
IGradientBasedOptimizer<T, TInput, TOutput> MetaOptimizer { get; set; } Optimizer for the meta-update.
ILossFunction<T> LossFunction { get; set; } Loss function for meta-training; null uses the default multi-class classification loss.
bool EnableCheckpointing { get; set; }
bool UseFirstOrder { get; set; } Whether to use the first-order approximation of the meta-gradient.
double InnerLearningRate { get; set; }
double OuterLearningRate { get; set; }
double QueryInfluenceWeight { get; set; } How much query gradient information influences the transform.
double TransformRegWeight { get; set; } Regularization on the learned transform parameters.
double? GradientClipThreshold { get; set; }
int AdaptationSteps { get; set; }
int CheckpointFrequency { get; set; }
int EvaluationFrequency { get; set; }
int EvaluationTasks { get; set; }
int MetaBatchSize { get; set; }
int NumMetaIterations { get; set; }
int TransductiveIterations { get; set; } Number of transductive iterations using query feedback.
int TransformDim { get; set; } Dimension of the embedding transform space.
int? RandomSeed { get; set; }

Methods

Method Summary
IMetaLearnerOptions<T> Clone()
bool IsValid()