easygraph.nn.convs package

Subpackages

• easygraph.nn.convs.hypergraphs package
  • Submodules
  • easygraph.nn.convs.hypergraphs.dhcf_conv module
    • JHConv
      • JHConv.forward()
      • JHConv.training
  • easygraph.nn.convs.hypergraphs.halfnlh_conv module
  • easygraph.nn.convs.hypergraphs.hgnn_conv module
    • HGNNConv
      • HGNNConv.forward()
      • HGNNConv.training
  • easygraph.nn.convs.hypergraphs.hgnnp_conv module
    • HGNNPConv
      • HGNNPConv.forward()
      • HGNNPConv.training
  • easygraph.nn.convs.hypergraphs.hnhn_conv module
    • HNHNConv
      • HNHNConv.forward()
      • HNHNConv.training
  • easygraph.nn.convs.hypergraphs.hypergcn_conv module
    • HyperGCNConv
      • HyperGCNConv.forward()
      • HyperGCNConv.training
  • easygraph.nn.convs.hypergraphs.unignn_conv module
    • UniGATConv
      • UniGATConv.forward()
      • UniGATConv.training
    • UniGCNConv
      • UniGCNConv.forward()
      • UniGCNConv.training
    • UniGINConv
      • UniGINConv.forward()
      • UniGINConv.training
    • UniSAGEConv
      • UniSAGEConv.forward()
      • UniSAGEConv.training
  • Module contents

Submodules

easygraph.nn.convs.common module

class easygraph.nn.convs.common.MultiHeadWrapper(num_heads: int, readout: str, layer: Module, **kwargs)

Bases: Module

A wrapper to apply multiple heads to a given layer.

Parameters:

• num_heads (int) – The number of heads.

• readout (bool) – The readout method. Can be "mean", "max", "sum", or "concat".

• layer (nn.Module) – The layer to apply multiple heads.

• **kwargs – The keyword arguments for the layer.

forward(**kwargs) → Tensor

The forward function.

Note

You must explicitly pass the keyword arguments to the layer. For example, if the layer is GATConv, you must pass X=X and g=g.

training: bool

easygraph.nn.convs.pma module

Module contents