EPNetOptions<T, TInput, TOutput>

Options & Configuration · AiDotNet.MetaLearning.Options

Configuration options for EPNet (Embedding Propagation Network) (Rodriguez et al., CVPR 2020).

Inheritance: ModelOptions → EPNetOptions<T, TInput, TOutput>

Implements: IMetaLearnerOptions<T>

For Beginners

EPNet refines features by spreading information:

  1. Extract features for all examples (support + query)
  2. Build a similarity graph connecting all examples
  3. Propagate feature information through the graph
  4. Features become more discriminative after propagation

It’s like a game of telephone where each example improves by hearing from its neighbors.

How It Works

EPNet propagates embeddings through a label propagation graph to refine features using both support and query set information in a transductive manner.

Reference: Rodriguez, P., Laradji, I., Drouin, A., & Lacoste, A. (2020). Embedding Propagation: Smoother Manifold for Few-Shot Classification. CVPR 2020.

Constructors

Constructor Summary
EPNetOptions(IFullModel<T, TInput, TOutput> metaModel) Initializes a new instance of EPNetOptions.

Properties

Property Summary
IEpisodicDataLoader<T, TInput, TOutput> DataLoader { get; set; } Gets or sets the episodic data loader.
IFullModel<T, TInput, TOutput> MetaModel { get; set; } Gets or sets the feature extractor model.
IGradientBasedOptimizer<T, TInput, TOutput> InnerOptimizer { get; set; } Must stay null: this algorithm takes no plain gradient inner step (it adapts without one, or by its own update rule), so a supplied optimizer is rejected when the learner is built.
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; }
double InnerLearningRate { get; set; }
double OuterLearningRate { get; set; }
double PropagationAlpha { get; set; } Gets or sets the propagation smoothing parameter (alpha).
double? GradientClipThreshold { get; set; }
int AdaptationSteps { get; set; } Number of gradient steps taken on each task’s support set (0: this algorithm adapts without gradient steps).
int CheckpointFrequency { get; set; }
int EvaluationFrequency { get; set; }
int EvaluationTasks { get; set; }
int MetaBatchSize { get; set; }
int NumMetaIterations { get; set; }
int NumNeighbors { get; set; } Gets or sets the number of nearest neighbors for the propagation graph.
int PropagationIterations { get; set; } Gets or sets the number of embedding propagation iterations.
int? RandomSeed { get; set; } Gets or sets the random seed.

Methods

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