GraphData<T>

Models & Types · AiDotNet.Data.Structures

Represents a single graph with nodes, edges, features, and optional labels.

For Beginners

Think of a graph as a social network:

  • Nodes: People in the network
  • Edges: Friendships or connections between people
  • Node Features: Each person’s attributes (age, interests, etc.)
  • Edge Features: Relationship attributes (how long they’ve been friends, interaction frequency)
  • Labels: What we want to predict (e.g., will this person like a product?)

This class packages all this information together for graph neural network training.

How It Works

GraphData encapsulates all information about a graph structure including:

  • Node features (attributes for each node)
  • Edge indices (connections between nodes)
  • Edge features (optional attributes for edges)
  • Adjacency matrix (graph structure in matrix form)
  • Labels (for supervised learning tasks)

Constructors

Constructor Summary
GraphData()

Properties

Property Summary
Dictionary<string, object> Metadata { get; set; } Metadata for heterogeneous graphs (optional).
Tensor<T> AdjacencyMatrix { get; set; } Adjacency matrix of shape [num_nodes, num_nodes] or [batch_size, num_nodes, num_nodes].
Tensor<T> EdgeFeatures { get; set; } Optional edge feature matrix of shape [num_edges, num_edge_features].
Tensor<T> EdgeIndex { get; set; } Edge index tensor of shape [2, num_edges] or [num_edges, 2].
Tensor<T> GraphLabel { get; set; } Graph-level label for graph-level tasks (e.g., graph classification).
Tensor<T> NodeFeatures { get; set; } Node feature matrix of shape [num_nodes, num_features].
Tensor<T> NodeLabels { get; set; } Node labels for node-level tasks (e.g., node classification).
Tensor<T> TestMask { get; set; } Mask indicating which nodes are in the test set.
Tensor<T> TrainMask { get; set; } Mask indicating which nodes are in the training set.
Tensor<T> ValMask { get; set; } Mask indicating which nodes are in the validation set.
int NumEdgeFeatures { get; } Number of edge features (0 if no edge features).
int NumEdges { get; } Number of edges in the graph.
int NumNodeFeatures { get; } Number of node features.
int NumNodes { get; } Number of nodes in the graph.