HyperShotOptions<T, TInput, TOutput>

Options & Configuration · AiDotNet.MetaLearning.Options

Configuration options for HyperShot (Sendera et al., NeurIPS 2023).

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

Implements: IMetaLearnerOptions<T>

For Beginners

HyperShot uses a “network that generates networks”:

  1. A hypernetwork takes support set features as input
  2. It outputs the weights for a classifier tailored to this task
  3. The generated classifier is used to classify query examples

This is faster than gradient-based adaptation (like MAML) because it requires only a single forward pass through the hypernetwork.

How It Works

HyperShot generates task-specific classifier weights using a hypernetwork conditioned on support set features. The hypernetwork produces a full classifier in one forward pass.

Reference: Sendera, M., Tabor, J., Nowak, A., & Trzcinski, T. (2023). HyperShot: Few-Shot Learning by Kernel HyperNetworks. NeurIPS 2023.

Constructors

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

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; } Must stay null: this algorithm takes no plain gradient inner step (it adapts without one, or by its own update rule), so a supplied optimizer is rejected when the learner is built.
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 InnerLearningRate { get; set; }
double OuterLearningRate { get; set; }
double? GradientClipThreshold { get; set; }
int AdaptationSteps { get; set; } Number of gradient steps taken on each task’s support 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 MetaBatchSize { get; set; }
int NumMetaIterations { get; set; }
int? RandomSeed { get; set; } Gets or sets the random seed.
string KernelType { get; set; } Gets or sets the kernel type for kernel hypernetwork.

Methods

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