GATModule Class Reference

Inheritance diagram for GATModule:

Collaboration diagram for GATModule:

Public Member Functions
def	__init__ (self, in_feats, units, num_heads, in_feats_glob, use_gap=False)
def	forward (self, graph, feat, feat_glob=None)

Public Attributes
	gat
	TODO.
	fc
	TODO.
	use_gap
	TODO.
	gap_gate
	TODO.
	gap
	TODO.

Detailed Description

Apply a GAT layer to node features, flatten outputs of attention heads
and update global features.

Definition at line 18 of file gatgap.py.

Constructor & Destructor Documentation

__init__()

def __init__	(		self,
			in_feats,
			units,
			num_heads,
			in_feats_glob,
			use_gap = False
	)

Initialise the class.
:param in_feats:  TODO
:param units:  TODO
:param num_heads:  TODO
:param in_feats_glob:  TODO
:param use_gap:  TODO

Definition at line 24 of file gatgap.py.

    ):
        """
        Initialise the class.
        :param in_feats:  TODO
        :param units:  TODO
        :param num_heads:  TODO
        :param in_feats_glob:  TODO
        :param use_gap:  TODO
        """
        super().__init__()
        
        self.gat = dglnn.GATConv(in_feats, units, num_heads)
        out_feats = units * num_heads
        
        self.fc = torch.nn.Linear(in_feats_glob + out_feats, units)
        
        self.use_gap = use_gap
        if self.use_gap:
            
            self.gap_gate = torch.nn.Linear(out_feats, 1)
            
            self.gap = GlobalAttentionPooling(self.gap_gate)
 

Member Function Documentation

forward()

def forward	(		self,
			graph,
			feat,
			feat_glob = None
	)

TODO

Definition at line 54 of file gatgap.py.

---

The documentation for this class was generated from the following file:

• generators/scripts/smartBKG/models/gatgap.py