torch_geometric.nn.conv.HypergraphConv

class HypergraphConv(in_channels: int, out_channels: int, use_attention: bool = False, attention_mode: str = 'node', heads: int = 1, concat: bool = True, negative_slope: float = 0.2, dropout: float = 0, bias: bool = True, **kwargs)[source]

Bases: MessagePassing

The hypergraph convolutional operator from the “Hypergraph Convolution and Hypergraph Attention” paper.

\[\mathbf{X}^{\prime} = \mathbf{D}^{-1} \mathbf{H} \mathbf{W} \mathbf{B}^{-1} \mathbf{H}^{\top} \mathbf{X} \mathbf{\Theta}\]

where \(\mathbf{H} \in {\{ 0, 1 \}}^{N \times M}\) is the incidence matrix, \(\mathbf{W} \in \mathbb{R}^M\) is the diagonal hyperedge weight matrix, and \(\mathbf{D}\) and \(\mathbf{B}\) are the corresponding degree matrices.

For example, in the hypergraph scenario \(\mathcal{G} = (\mathcal{V}, \mathcal{E})\) with \(\mathcal{V} = \{ 0, 1, 2, 3 \}\) and \(\mathcal{E} = \{ \{ 0, 1, 2 \}, \{ 1, 2, 3 \} \}\), the hyperedge_index is represented as:

hyperedge_index = torch.tensor([
    [0, 1, 2, 1, 2, 3],
    [0, 0, 0, 1, 1, 1],
])
Parameters:

  • in_channels (int) – Size of each input sample, or -1 to derive the size from the first input(s) to the forward method.

  • out_channels (int) – Size of each output sample.

  • use_attention (bool, optional) – If set to True, attention will be added to this layer. (default: False)

  • attention_mode (str, optional) – The mode on how to compute attention. If set to "node", will compute attention scores of nodes within all nodes belonging to the same hyperedge. If set to "edge", will compute attention scores of nodes across all edges holding this node belongs to. (default: "node")

  • heads (int, optional) – Number of multi-head-attentions. (default: 1)

  • concat (bool, optional) – If set to False, the multi-head attentions are averaged instead of concatenated. (default: True)

  • negative_slope (float, optional) – LeakyReLU angle of the negative slope. (default: 0.2)

  • dropout (float, optional) – Dropout probability of the normalized attention coefficients which exposes each node to a stochastically sampled neighborhood during training. (default: 0)

  • bias (bool, optional) – If set to False, the layer will not learn an additive bias. (default: True)

  • **kwargs (optional) – Additional arguments of torch_geometric.nn.conv.MessagePassing.

Shapes:

  • input: node features \((|\mathcal{V}|, F_{in})\), hyperedge indices \((|\mathcal{V}|, |\mathcal{E}|)\), hyperedge weights \((|\mathcal{E}|)\) (optional) hyperedge features \((|\mathcal{E}|, D)\) (optional)

  • output: node features \((|\mathcal{V}|, F_{out})\)

forward(x: Tensor, hyperedge_index: Tensor, hyperedge_weight: Optional[Tensor] = None, hyperedge_attr: Optional[Tensor] = None, num_edges: Optional[int] = None) → Tensor[source]

Runs the forward pass of the module.

Parameters:

  • x (torch.Tensor) – Node feature matrix \(\mathbf{X} \in \mathbb{R}^{N \times F}\).

  • hyperedge_index (torch.Tensor) – The hyperedge indices, i.e. the sparse incidence matrix \(\mathbf{H} \in {\{ 0, 1 \}}^{N \times M}\) mapping from nodes to edges.

  • hyperedge_weight (torch.Tensor, optional) – Hyperedge weights \(\mathbf{W} \in \mathbb{R}^M\). (default: None)

  • hyperedge_attr (torch.Tensor, optional) – Hyperedge feature matrix in \(\mathbb{R}^{M \times F}\). These features only need to get passed in case use_attention=True. (default: None)

  • num_edges (int, optional) – The number of edges \(M\). (default: None)

reset_parameters()[source]

Resets all learnable parameters of the module.