Struct GraphConvolution 

pub struct GraphConvolution { /* private fields */ }

Graph Convolutional Network (GCN) layer

Implements the GCN operation: H^(l+1) = σ(D^(-1/2) A D^(-1/2) H^(l) W^(l)) where A is the adjacency matrix, D is the degree matrix, H is node features, W is weights

Implementations

impl GraphConvolution

pub fn new( in_features: usize, out_features: usize, use_bias: bool, add_self_loops: bool, normalize: bool, ) -> TorshResult<Self>

Create a new graph convolution layer

pub fn forward( &self, node_features: &Tensor, adjacency: &CsrTensor, ) -> TorshResult<Tensor>

Forward pass through the graph convolution layer

pub fn num_parameters(&self) -> usize

Get the number of parameters

pub fn in_features(&self) -> usize

Get input feature dimension

pub fn out_features(&self) -> usize

Get output feature dimension