DPGNOptions<T, TInput, TOutput>

Options & Configuration · AiDotNet.MetaLearning.Options

Configuration options for DPGN (Distribution Propagation Graph Network) (Yang et al., CVPR 2020).

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

Implements: IMetaLearnerOptions<T>

For Beginners

DPGN builds two graphs to pass information:

  1. Point graph: Passes feature information between examples (like GNN meta-learning)
  2. Distribution graph: Passes uncertainty/confidence information
  3. Both graphs refine each other iteratively

The dual approach captures both “what features are similar” and “how confident we are about similarities.”

How It Works

DPGN uses a dual graph structure to propagate both point estimates and distribution information between support and query examples for few-shot classification.

Reference: Yang, L., Li, L., Zhang, Z., Zhou, X., Zhou, E., & Liu, Y. (2020). DPGN: Distribution Propagation Graph Network for Few-Shot Learning. CVPR 2020.

Constructors

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

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? GradientClipThreshold { get; set; }
int AdaptationSteps { get; set; } Number of gradient steps taken on each task’s support set.
int CheckpointFrequency { get; set; }
int EdgeFeatureDim { get; set; } Gets or sets the edge feature dimension.
int EvaluationFrequency { get; set; }
int EvaluationTasks { get; set; }
int MetaBatchSize { get; set; }
int NodeFeatureDim { get; set; } Gets or sets the graph node feature dimension.
int NumMetaIterations { get; set; }
int NumPropagationLayers { get; set; } Gets or sets the number of graph propagation layers.
int? RandomSeed { get; set; } Gets or sets the random seed.

Methods

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