GNNMetaOptions<T, TInput, TOutput>
Options & Configuration · AiDotNet.MetaLearning.Options
Configuration options for the Graph Neural Network Meta-learning algorithm.
Inheritance: ModelOptions → GNNMetaOptions<T, TInput, TOutput>
Implements: IMetaLearnerOptions<T>
For Beginners
GNN Meta-learning treats the learning process as a graph problem:
- Each task or example becomes a node in a graph
- Relationships between tasks are edges (e.g., task similarity)
- A graph neural network learns to propagate useful information
- This allows the model to leverage task relationships for better adaptation
Imagine a social network where users are tasks and friendships are similarities. By looking at what similar tasks learned, new tasks can adapt faster.
How It Works
GNN-based meta-learning models tasks and examples as nodes in a graph, with edges representing relationships between them. The graph neural network learns to propagate information across the task structure to improve learning.
Key Components:
- Node Embeddings: Represent tasks/examples as vectors
- Message Passing: Share information between connected nodes
- Graph Aggregation: Combine node information for predictions
Constructors
| Constructor | Summary |
|---|---|
GNNMetaOptions(IFullModel<T, TInput, TOutput> metaModel) |
Initializes a new instance of the GNNMetaOptions class with the required meta-model. |
Properties
| Property | Summary |
|---|---|
GNNAggregationType AggregationType { get; set; } |
Gets or sets the aggregation method for graph-level representations. |
IEpisodicDataLoader<T, TInput, TOutput> DataLoader { get; set; } |
Gets or sets the episodic data loader for sampling tasks. |
IFullModel<T, TInput, TOutput> MetaModel { get; set; } |
Gets or sets the meta-model to be trained. |
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 meta-model’s default loss. |
TaskSimilarityMetric SimilarityMetric { get; set; } |
Gets or sets how task similarity is computed for building the task graph. |
bool EnableCheckpointing { get; set; } |
Gets or sets whether to save checkpoints during training. |
bool LearnEdgeWeights { get; set; } |
Gets or sets whether to learn edge weights during training. |
bool UseFirstOrder { get; set; } |
Gets or sets whether to use first-order approximation. |
bool UseFullyConnectedGraph { get; set; } |
Gets or sets whether to use a fully connected task graph. |
bool UseLayerNorm { get; set; } |
Gets or sets whether to use layer normalization in GNN layers. |
bool UseResidualConnections { get; set; } |
Gets or sets whether to use residual connections in GNN layers. |
double DropoutRate { get; set; } |
Gets or sets the dropout rate for GNN layers. |
double EdgeThreshold { get; set; } |
Gets or sets the threshold for creating edges between tasks. |
double InnerLearningRate { get; set; } |
Gets or sets the learning rate for the inner loop (task adaptation). |
double OuterLearningRate { get; set; } |
Gets or sets the learning rate for the outer loop (meta-update). |
double? GradientClipThreshold { get; set; } |
Gets or sets the maximum gradient norm for gradient clipping. |
int AdaptationSteps { get; set; } |
Gets or sets the number of gradient steps to take during inner loop adaptation. |
int CheckpointFrequency { get; set; } |
Gets or sets how often to save checkpoints. |
int EdgeFeatureDimension { get; set; } |
Gets or sets the dimension of edge features in the task graph. |
int EvaluationFrequency { get; set; } |
Gets or sets how often to evaluate during meta-training. |
int EvaluationTasks { get; set; } |
Gets or sets the number of tasks to use for evaluation. |
int GNNHiddenDimension { get; set; } |
Gets or sets the hidden dimension for the GNN layers. |
int MaxNeighbors { get; set; } |
Gets or sets the maximum number of neighbors per node in sparse graph. |
int MetaBatchSize { get; set; } |
Gets or sets the number of tasks to sample per meta-training iteration. |
int NodeEmbeddingDimension { get; set; } |
Gets or sets the dimension of node embeddings in the task graph. |
int NumAttentionHeads { get; set; } |
Gets or sets the number of attention heads for graph attention. |
int NumMessagePassingLayers { get; set; } |
Gets or sets the number of message passing layers in the GNN. |
int NumMetaIterations { get; set; } |
Gets or sets the total number of meta-training iterations to perform. |
int? RandomSeed { get; set; } |
Gets or sets the random seed for reproducibility. |
Methods
| Method | Summary |
|---|---|
IMetaLearnerOptions<T> Clone() |
Creates a deep copy of the GNN Meta options. |
bool IsValid() |
Validates that all GNN Meta configuration options are properly set. |