openhgnn.models.RGCN

class RGCN(in_dim, hidden_dim, out_dim, etypes, num_bases, num_hidden_layers=1, dropout=0, use_self_loop=False)[source]

Title: Modeling Relational Data with Graph Convolutional Networks

Authors: Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, Max Welling

Parameters:

  • in_dim (int) – Input feature size.

  • hidden_dim (int) – Hidden dimension .

  • out_dim (int) – Output feature size.

  • etypes (list[str]) – Relation names.

  • num_bases (int, optional) – Number of bases. If is none, use number of relations. Default: None.

  • num_hidden_layers (int) – Number of RelGraphConvLayer

  • dropout (float, optional) – Dropout rate. Default: 0.0

  • use_self_loop (bool, optional) – True to include self loop message. Default: False

RelGraphConvLayer
Type:

RelGraphConvLayer