Class BOILOptions<T, TInput, TOutput>

Namespace

AiDotNet.MetaLearning.Options

Assembly

AiDotNet.dll

Configuration options for Body Only Inner Loop (BOIL) algorithm.

public class BOILOptions<T, TInput, TOutput> : IMetaLearnerOptions<T>

Type Parameters

T

The numeric data type used for calculations (e.g., float, double).

TInput

The input data type (e.g., Matrix<T>, Tensor<T>).

TOutput

The output data type (e.g., Vector<T>, Tensor<T>).

Inheritance

object

BOILOptions<T, TInput, TOutput>

Implements

IMetaLearnerOptions<T>

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.MemberwiseClone()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

BOIL is the opposite of ANIL - it only adapts the feature extractor (body) during inner-loop adaptation while keeping the classification head frozen. This explores the hypothesis that task-specific features are more important than task-specific classifiers.

For Beginners: BOIL splits a neural network into two parts:

1. Body (Feature Extractor): ADAPTED for each new task
2. Head (Classifier): FROZEN during adaptation (uses meta-learned weights)

This is the opposite of ANIL (which freezes body, adapts head). BOIL tests whether it's better to adapt HOW we see things rather than HOW we decide.

When to use BOIL: - When tasks differ more in their visual/input patterns than their decision boundaries - When you have a good meta-learned classifier that works across tasks - When you want to experiment with different adaptation strategies

Reference: Oh, J., Yoo, H., Kim, C., & Yun, S. Y. (2021). BOIL: Towards Representation Change for Few-shot Learning.

Constructors

BOILOptions(IFullModel<T, TInput, TOutput>)

Initializes a new instance of the BOILOptions class with the required meta-model.

public BOILOptions(IFullModel<T, TInput, TOutput> metaModel)

Parameters

metaModel IFullModel<T, TInput, TOutput>

The neural network to be trained (required).

Exceptions

ArgumentNullException

Thrown when metaModel is null.

Properties

AdaptationSteps

Gets or sets the number of adaptation steps (gradient steps on support set).

public int AdaptationSteps { get; set; }

Property Value

int

Default is 5.

BodyAdaptationFraction

Gets or sets the fraction of body parameters to adapt (for efficiency).

public double BodyAdaptationFraction { get; set; }

Property Value

double

Default is 1.0 (adapt all body parameters).

Remarks

For Beginners: If your body has millions of parameters, adapting all of them might be slow. This setting lets you adapt only a fraction (e.g., 0.5 = adapt only half the body parameters).

BodyL2Regularization

Gets or sets the L2 regularization strength for the body.

public double BodyL2Regularization { get; set; }

Property Value

double

Default is 0.0 (no regularization).

CheckpointFrequency

Gets or sets how often to save checkpoints.

public int CheckpointFrequency { get; set; }

Property Value

int

DataLoader

Gets or sets the episodic data loader for sampling tasks. Default: null (tasks must be provided manually to MetaTrain).

public IEpisodicDataLoader<T, TInput, TOutput>? DataLoader { get; set; }

Property Value

IEpisodicDataLoader<T, TInput, TOutput>

EarlyLayerLrMultiplier

Gets or sets the learning rate multiplier for earlier layers (if using layerwise rates).

public double EarlyLayerLrMultiplier { get; set; }

Property Value

double

Default is 0.1 (earlier layers update 10x slower).

EnableCheckpointing

Gets or sets whether to save model checkpoints.

public bool EnableCheckpointing { get; set; }

Property Value

bool

EvaluationFrequency

Gets or sets how often to evaluate the meta-learner.

public int EvaluationFrequency { get; set; }

Property Value

int

EvaluationTasks

Gets or sets the number of tasks to use for evaluation.

public int EvaluationTasks { get; set; }

Property Value

int

FeatureDimension

Gets or sets the dimension of the final feature representation (before head).

public int FeatureDimension { get; set; }

Property Value

int

Default is 512.

GradientClipThreshold

Gets or sets the maximum gradient norm for gradient clipping.

public double? GradientClipThreshold { get; set; }

Property Value

double?

Default is 10.0.

InnerLearningRate

Gets or sets the learning rate for the inner loop (body adaptation).

public double InnerLearningRate { get; set; }

Property Value

double

Default is 0.01.

InnerOptimizer

Gets or sets the optimizer for inner loop updates (body only). Default: null (uses SGD with InnerLearningRate).

public IGradientBasedOptimizer<T, TInput, TOutput>? InnerOptimizer { get; set; }

Property Value

IGradientBasedOptimizer<T, TInput, TOutput>

LossFunction

Gets or sets the loss function for training. Default: null (uses cross-entropy loss internally).

public ILossFunction<T>? LossFunction { get; set; }

Property Value

ILossFunction<T>

MetaBatchSize

Gets or sets the number of tasks to sample per meta-training iteration.

public int MetaBatchSize { get; set; }

Property Value

int

Default is 4.

MetaModel

Gets or sets the meta-model to be trained. This is the only required property.

public IFullModel<T, TInput, TOutput> MetaModel { get; set; }

Property Value

IFullModel<T, TInput, TOutput>

Remarks

The meta-model should be a neural network with a separable body (feature extractor) and head (classifier). Only the body will be adapted during the inner loop.

MetaOptimizer

Gets or sets the optimizer for meta-parameter (outer loop) updates. Default: null (uses built-in Adam optimizer with OuterLearningRate).

public IGradientBasedOptimizer<T, TInput, TOutput>? MetaOptimizer { get; set; }

Property Value

IGradientBasedOptimizer<T, TInput, TOutput>

NumClasses

Gets or sets the number of output classes.

public int NumClasses { get; set; }

Property Value

int

Default is 5.

NumMetaIterations

Gets or sets the total number of meta-training iterations.

public int NumMetaIterations { get; set; }

Property Value

int

Default is 1000.

OuterLearningRate

Gets or sets the learning rate for the outer loop (meta-update).

public double OuterLearningRate { get; set; }

Property Value

double

Default is 0.001.

RandomSeed

Gets or sets the random seed for reproducibility.

public int? RandomSeed { get; set; }

Property Value

int?

ReinitializeBody

Gets or sets whether to reinitialize the body for each task.

public bool ReinitializeBody { get; set; }

Property Value

bool

Default is false (use meta-learned initialization).

UseFirstOrder

Gets or sets whether to use first-order approximation.

public bool UseFirstOrder { get; set; }

Property Value

bool

Default is true (BOIL typically uses first-order for efficiency).

UseLayerwiseLearningRates

Gets or sets whether to use layer-wise learning rates for the body.

public bool UseLayerwiseLearningRates { get; set; }

Property Value

bool

Default is false.

Remarks

For Beginners: Different layers might need different learning rates. Earlier layers (close to input) might need smaller updates than later layers.

Methods

Clone()

Creates a deep copy of the BOIL options.

public IMetaLearnerOptions<T> Clone()

Returns

IMetaLearnerOptions<T>

A new BOILOptions instance with the same configuration.

IsValid()

Validates that all BOIL configuration options are properly set.

public bool IsValid()

Returns

bool

True if the configuration is valid; otherwise, false.