GIN
- class dhg.models.GIN(*args, **kwargs)[source]
Bases:
torch.nn.Module
The GIN model proposed in How Powerful are Graph Neural Networks? paper (ICLR 2019).
- Parameters
in_channels (
int
) – \(C_{in}\) is the number of input channels.hid_channels (
int
) – \(C_{hid}\) is the number of hidden channels.num_classes (
int
) – The Number of class of the classification task.num_layers (
int
) – The number of layers in the GIN model. In the original code, it is set to5
.num_mlp_layers (
int
) – The number of layers in the MLP. Defaults to2
.eps (
float
) – The epsilon value. Defaults to0.0
.train_eps (
bool
) – If set toTrue
, the epsilon value will be trainable. Defaults toFalse
.use_bn (
bool
) – If set toTrue
, use batch normalization. Defaults toFalse
.drop_rate (
float
) – The dropout ratio. Defaults to0.5
.