SDCLOptions<T, TInput, TOutput>
Options & Configuration · AiDotNet.MetaLearning.Options
Configuration options for SDCL: Self-Distillation Collaborative Learning for meta-learning.
Inheritance: ModelOptions → SDCLOptions<T, TInput, TOutput>
Implements: IMetaLearnerOptions<T>
How It Works
SDCL applies self-distillation within the meta-learning framework. A teacher model (exponential moving average of the student) provides soft targets that regularize the adapted student’s predictions. The KL divergence between teacher and student predictions acts as a collaborative learning signal that stabilizes adaptation and improves cross-domain generalization.
Constructors
| Constructor | Summary |
|---|---|
SDCLOptions(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 DistillationTemperature { get; set; } |
Temperature for softening teacher/student predictions. |
double DistillationWeight { get; set; } |
Weight for the distillation (KL divergence) loss. |
double InnerLearningRate { get; set; } |
|
double OuterLearningRate { get; set; } |
|
double TeacherEmaDecay { get; set; } |
EMA decay rate for the teacher model. |
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? RandomSeed { get; set; } |
Methods
| Method | Summary |
|---|---|
IMetaLearnerOptions<T> Clone() |
|
bool IsValid() |