ActiveTransFSLOptions<T, TInput, TOutput>
Options & Configuration ยท AiDotNet.MetaLearning.Options
Configuration options for ActiveTransFSL (Active Transductive Few-Shot Learning).
Inheritance: ModelOptions โ ActiveTransFSLOptions<T, TInput, TOutput>
Implements: IMetaLearnerOptions<T>
How It Works
ActiveTransFSL combines active learning with transductive inference. After initial adaptation on support data, it uses gradient-norm-based uncertainty to identify the most uncertain parameter dimensions, then performs transductive refinement steps that focus adaptation on these uncertain regions using query data feedback.
Constructors
| Constructor | Summary |
|---|---|
ActiveTransFSLOptions(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 SelectionFraction { get; set; } |
Fraction of parameters (by uncertainty) to actively refine. |
double TransductiveLR { get; set; } |
Learning rate for transductive refinement. |
double TransductiveWeight { get; set; } |
Weight on the transductive (query-feedback) loss. |
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 TransductiveRefinementSteps { get; set; } |
Number of transductive refinement steps using query gradients. |
int? RandomSeed { get; set; } |
Methods
| Method | Summary |
|---|---|
IMetaLearnerOptions<T> Clone() |
|
bool IsValid() |