HyperMAMLOptions<T, TInput, TOutput>

Options & Configuration · AiDotNet.MetaLearning.Options

Configuration options for HyperMAML (hypernetwork-based MAML initialization).

Inheritance: ModelOptions → HyperMAMLOptions<T, TInput, TOutput>

Implements: IMetaLearnerOptions<T>

For Beginners

HyperMAML improves MAML’s starting point:

  • MAML: Same initialization for every task
  • HyperMAML: Custom initialization for each task, generated by a hypernetwork

The hypernetwork looks at the support set and produces an initialization that’s already close to the task-specific optimum, requiring fewer adaptation steps.

How It Works

HyperMAML uses a hypernetwork to generate task-specific initial parameters for MAML, rather than using a single shared initialization. The hypernetwork conditions on support set statistics to produce a better starting point for each task.

Constructors

Constructor Summary
HyperMAMLOptions(IFullModel<T, TInput, TOutput> metaModel) Initializes a new instance of HyperMAMLOptions.

Properties

Property Summary
IEpisodicDataLoader<T, TInput, TOutput> DataLoader { get; set; } Gets or sets the episodic data loader.
IFullModel<T, TInput, TOutput> MetaModel { get; set; } Gets or sets the feature extractor model.
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; }
double BlendFactor { get; set; } Gets or sets the blend factor between shared and task-specific initialization.
double InnerLearningRate { get; set; }
double OuterLearningRate { get; set; }
double? GradientClipThreshold { get; set; }
int AdaptationSteps { get; set; }
int CheckpointFrequency { get; set; }
int EvaluationFrequency { get; set; }
int EvaluationTasks { get; set; }
int HypernetHiddenDim { get; set; } Gets or sets the hypernetwork hidden dimension.
int HypernetNumLayers { get; set; } Gets or sets the number of hypernetwork layers.
int MetaBatchSize { get; set; }
int NumMetaIterations { get; set; }
int? RandomSeed { get; set; } Gets or sets the random seed.

Methods

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