UniGCNConv
- class dhg.nn.UniGCNConv(*args, **kwargs)[source]
Bases:
torch.nn.ModuleThe UniGCN convolution layer proposed in UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks paper (IJCAI 2021).
Sparse Format:
\[\begin{split}\left\{ \begin{aligned} h_{e} &= \frac{1}{|e|} \sum_{j \in e} x_{j} \\ \tilde{x}_{i} &= \frac{1}{\sqrt{d_{i}}} \sum_{e \in \tilde{E}_{i}} \frac{1}{\sqrt{\tilde{d}_{e}}} W h_{e} \end{aligned} \right. .\end{split}\]where \(\tilde{d}_{e} = \frac{1}{|e|} \sum_{i \in e} d_{i}\).
Matrix Format:
\[\mathbf{X}^{\prime} = \sigma \left( \mathbf{D}_v^{-\frac{1}{2}} \mathbf{H} \tilde{\mathbf{D}}_e^{-\frac{1}{2}} \cdot \mathbf{D}_e^{-1} \mathbf{H}^\top \mathbf{X} \mathbf{\Theta} \right) .\]- Parameters
in_channels (
int) – \(C_{in}\) is the number of input channels.out_channels (int) – \(C_{out}\) is the number of output channels.
bias (
bool) – If set toFalse, the layer will not learn the bias parameter. Defaults toTrue.use_bn (
bool) – If set toTrue, the layer will use batch normalization. Defaults toFalse.drop_rate (
float) – If set to a positive number, the layer will use dropout. Defaults to0.5.is_last (
bool) – If set toTrue, the layer will not apply the final activation and dropout functions. Defaults toFalse.