gammagl.layers.conv.RGCNConv

class RGCNConv(in_channels, out_channels, num_relations: int, num_bases=None, num_blocks=None, root_weight: bool = True, add_bias=True)

The relational graph convolutional operator from the “Modeling Relational Data with Graph Convolutional Networks” paper

\[\mathbf{x}^{\prime}_i = \mathbf{\Theta}_{\textrm{root}} \cdot \mathbf{x}_i + \sum_{r \in \mathcal{R}} \sum_{j \in \mathcal{N}_r(i)} \frac{1}{|\mathcal{N}_r(i)|} \mathbf{\Theta}_r \cdot \mathbf{x}_j\]

where \(\mathcal{R}\) denotes the set of relations, i.e. edge types. Edge type needs to be a one-dimensional torch.long tensor which stores a relation identifier \(\in \{ 0, \ldots, |\mathcal{R}| - 1\}\) for each edge.

forward(x, edge_index, edge_type=None)

Parameters:

• x – The input node features. Can be either a [num_nodes, in_channels] node feature matrix, or an optional one-dimensional node index tensor (in which case input features are treated as trainable node embeddings). Furthermore, x can be of type tuple denoting source and destination node features.

• edge_index – edge index

• edge_type – The one-dimensional relation type/index for each edge in edge_index. Should be only None in case edge_index is of type torch_sparse.tensor.SparseTensor. (default: None)