Struct GNNConfig 

pub struct GNNConfig {
    pub num_layers: usize,
    pub hidden_dim: usize,
    pub output_dim: usize,
    pub aggregation: AggregationType,
    pub activation: ActivationType,
    pub dropout: f64,
    pub add_self_loops: bool,
    pub layer_norm: bool,
}

Configuration for GNN inference.

Fields

num_layers: usize

Number of message passing layers.

hidden_dim: usize

Hidden dimension size.

output_dim: usize

Output dimension (number of classes or embedding size).

aggregation: AggregationType

Aggregation function for messages.

activation: ActivationType

Activation function.

dropout: f64

Dropout rate (0-1).

add_self_loops: bool

Whether to add self-loops.

layer_norm: bool

Whether to use layer normalization.

Trait Implementations

impl Clone for GNNConfig

fn clone(&self) -> GNNConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for GNNConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for GNNConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for GNNConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for GNNConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.