class LGConv(normalize: bool = True, **kwargs)[source]

Bases: MessagePassing

The Light Graph Convolution (LGC) operator from the “LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation” paper.

\[\mathbf{x}^{\prime}_i = \sum_{j \in \mathcal{N}(i)} \frac{e_{j,i}}{\sqrt{\deg(i)\deg(j)}} \mathbf{x}_j\]
  • input: node features \((|\mathcal{V}|, F)\), edge indices \((2, |\mathcal{E}|)\), edge weights \((|\mathcal{E}|)\) (optional)

  • output: node features \((|\mathcal{V}|, F)\)

forward(x: Tensor, edge_index: Union[Tensor, SparseTensor], edge_weight: Optional[Tensor] = None) Tensor[source]

Runs the forward pass of the module.

reset_parameters() None

Resets all learnable parameters of the module.