openhgnn.layers.MacroConv

class MacroConv(in_feats: int, out_feats: int, num_heads: int, dropout: float = 0.0, negative_slope: float = 0.2)[source]
Parameters:

  • in_feats (int) – Input feature size.

  • out_feats (int) – Output feature size.

  • num_heads (int) – Number of heads in Multi-Head Attention.

  • dropout (float, optional) – Dropout rate, defaults: 0.