UnsupervisedMetaLearnOptions<T, TInput, TOutput>

Options & Configuration ยท AiDotNet.MetaLearning.Options

Configuration options for Unsupervised Meta-Learning (Hsu et al., 2019).

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

Implements: IMetaLearnerOptions<T>

How It Works

CACTUs (Hsu, Levine and Finn, ICLR 2019) builds pseudo-tasks by k-means clustering the unlabeled meta-training inputs and treating clusters as classes, then meta-trains MAML on them.

Constructors

Constructor Summary
UnsupervisedMetaLearnOptions(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? GradientClipThreshold { get; set; }
int AdaptationSteps { get; set; }
int CheckpointFrequency { get; set; }
int EvaluationFrequency { get; set; }
int EvaluationTasks { get; set; }
int KMeansIterations { get; set; } Lloyd iterations per k-means partition.
int MetaBatchSize { get; set; }
int NumClusters { get; set; } k, the number of k-means clusters each CACTUs partition of the unlabeled pool has.
int NumMetaIterations { get; set; }
int? RandomSeed { get; set; }

Methods

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