MetaLoRABankOptions<T, TInput, TOutput>

Options & Configuration ยท AiDotNet.MetaLearning.Options

Configuration options for Meta-LoRA Bank (2024).

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

Implements: IMetaLearnerOptions<T>

How It Works

Meta-LoRA Bank maintains a bank of diverse LoRA modules. For a new task, the algorithm selects and combines the most relevant modules using a task-conditioned gating mechanism. Meta-learning optimizes both the LoRA modules in the bank and the gating network.

Constructors

Constructor Summary
MetaLoRABankOptions(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 GatingTemperature { get; set; } Softmax temperature for module selection gating.
double InnerLearningRate { get; set; }
double LoadBalanceRegularization { get; set; } Load balancing regularization to encourage uniform module utilization.
double OuterLearningRate { get; set; }
double? GradientClipThreshold { get; set; }
int AdaptationSteps { get; set; }
int BankSize { get; set; } Number of LoRA modules in the bank.
int CheckpointFrequency { get; set; }
int EvaluationFrequency { get; set; }
int EvaluationTasks { get; set; }
int MetaBatchSize { get; set; }
int NumMetaIterations { get; set; }
int Rank { get; set; } Rank of each individual LoRA module.
int TopK { get; set; } Number of top modules to select per task (top-K gating).
int? RandomSeed { get; set; }

Methods

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