GraphNeuralOperator<T>
Models & Types ยท AiDotNet.PhysicsInformed.NeuralOperators
Implements Graph Neural Operators for learning operators on graph-structured data.
Inheritance: NeuralNetworkBase<T> โ GraphNeuralOperator<T>
How It Works
For Beginners: Graph Neural Operators extend neural operators to irregular, graph-structured domains.
Why Graphs? Many physical systems are naturally represented as graphs:
- Molecular structures (atoms = nodes, bonds = edges)
- Mesh-based simulations (mesh points = nodes, connectivity = edges)
- Traffic networks (intersections = nodes, roads = edges)
- Social networks, power grids, etc.
Regular operators (FNO, DeepONet) work on:
- Structured grids (images, regular spatial domains)
- Euclidean spaces
Graph operators work on:
- Irregular geometries
- Non-Euclidean spaces
- Variable-size domains
Key Idea - Message Passing: Information propagates through the graph via message passing:
- Each node has features (e.g., temperature, velocity)
- Nodes send messages to neighbors
- Nodes aggregate messages and update their features
- Repeat for multiple layers
Applications:
- Molecular dynamics (predict molecular properties)
- Computational fluid dynamics (irregular meshes)
- Material science (crystal structures)
- Climate modeling (irregular Earth grids)
- Particle systems
Example
var gno = new GraphNeuralOperator<float>();
Constructors
| Constructor | Summary |
|---|---|
GraphNeuralOperator() |
Initializes a new instance with default architecture settings. |
GraphNeuralOperator(NeuralNetworkArchitecture<T> architecture, IGradientBasedOptimizer<T, Tensor<T>, Tensor<T>> optimizer, GraphNeuralOperatorOptions options) |
Properties
| Property | Summary |
|---|---|
bool SupportsTraining { get; } |
Methods
| Method | Summary |
|---|---|
Dictionary<string, Tensor<T>> GetNamedLayerActivations(Tensor<T> input) |
|
ModelMetadata<T> GetModelMetadata() |
Gets metadata about the graph neural operator. |
Tensor<T> Forward(Tensor<T> input) |
Forward pass using an identity adjacency matrix. |
Tensor<T> Forward(Tensor<T> nodeFeatures, Tensor<T> adjacencyMatrix) |
Serializes graph operator-specific data. |
Tensor<T> ForwardForTraining(Tensor<T> input) |
|
Vector<T> GetGradients() |