GraphSAGEConv

class dhg.nn.GraphSAGEConv(*args, **kwargs)[source]

Bases: torch.nn.Module

The GraphSAGE convolution layer proposed in Inductive Representation Learning on Large Graphs paper (NeurIPS 2017).

\[\mathbf{x}^{\prime}_i = \mathbf{W}_1 \mathbf{x}_i + \mathbf{W}_2 \cdot \mathrm{mean}_{j \in \mathcal{N(i)}} \mathbf{x}_j\]

Parameters

in_channels (int) – \(C_{in}\) is the number of input channels.
out_channels (int) – \(C_{out}\) is the number of output channels.
aggr (str) – The neighbor aggregation method. Currently, only mean aggregation is supported. Defaults to “mean”.
bias (bool) – If set to False, the layer will not learn the bias parameter. Defaults to True.
use_bn (bool) – If set to True, the layer will use batch normalization. Defaults to False.
drop_rate (float) – The dropout probability. If dropout <= 0, the layer will not drop values. Defaults to 0.5.
is_last (bool) – If set to True, the layer will not apply the final activation and dropout functions. Defaults to False.

forward(X, g)[source]

The forward function.

Parameters