FreqPromptAlgorithm<T, TInput, TOutput>
Models & Types · AiDotNet.MetaLearning.Algorithms
Implementation of FreqPrompt: Frequency-domain prompt tuning for few-shot learning.
Inheritance: ModelBase<T, TInput, TOutput> → MetaLearnerBase<T, TInput, TOutput> → FreqPromptAlgorithm<T, TInput, TOutput>
Implements: IGeneratedParameterRegistrar<T>
How It Works
FreqPrompt meta-learns a set of frequency basis vectors and their coefficients that act as additive “prompts” in the parameter space. During adaptation, only the prompt coefficients are updated (the backbone is frozen), which enables efficient adaptation with very few parameters. Low-frequency prompts capture coarse domain shifts while high-frequency prompts handle fine-grained adjustments.
Algorithm:
Constructors
| Constructor | Summary |
|---|---|
FreqPromptAlgorithm(FreqPromptOptions<T, TInput, TOutput> options) |
Properties
| Property | Summary |
|---|---|
MetaLearningAlgorithmType AlgorithmType { get; } |
Methods
| Method | Summary |
|---|---|
IModel<TInput, TOutput, ModelMetadata<T>> Adapt(IMetaLearningTask<T, TInput, TOutput> task) |
|
T MetaTrain(TaskBatch<T, TInput, TOutput> taskBatch) |