torch_geometric_signed_directed.nn.general.conv_base

Classes

Conv_Base

The base class for mixed-path aggregation model, a convolution sub-model, from the

Functions

conv_norm_rw(edge_index[, fill_value, edge_weight, ...])

Module Contents

conv_norm_rw(edge_index, fill_value=0.5, edge_weight=None, num_nodes=None, add_self_loops=True, dtype=None)
class Conv_Base(fill_value: float = 0.5, cached: bool = False, add_self_loops: bool = True, normalize: bool = True, **kwargs)

Bases: torch_geometric.nn.conv.MessagePassing

The base class for mixed-path aggregation model, a convolution sub-model, from the DIGRAC: Digraph Clustering Based on Flow Imbalance paper. .. math:

\mathbf{X}^{\prime} = \mathbf{\hat{D}}^{-1/2} \mathbf{\hat{A}}
\mathbf{\hat{D}}^{-1/2} \mathbf{X} \mathbf{\Theta},

where \(\mathbf{\hat{A}} = \mathbf{A} + \mathbf{I}\) denotes the adjacency matrix with inserted self-loops and \(\hat{D}_{ii} = \sum_{j=0} \hat{A}_{ij}\) its diagonal degree matrix. The adjacency matrix can include other values than 1 representing edge weights via the optional edge_weight tensor. Its node-wise formulation is given by: .. math:

\mathbf{x}^{\prime}_i = \mathbf{\Theta} \sum_{j \in \mathcal{N}(v) \cup
\{ i \}} \frac{e_{j,i}}{\sqrt{\hat{d}_j \hat{d}_i}} \mathbf{x}_j

with \(\hat{d}_i = 1 + \sum_{j \in \mathcal{N}(i)} e_{j,i}\), where \(e_{j,i}\) denotes the edge weight from source node j to target node i (default: 1.0)

Parameters:

  • fill_value (float, optional) – The layer computes \(\mathbf{\hat{A}}\) as \(\mathbf{A} + fill_value*\mathbf{I}\). (default: 0.5)

  • cached (bool, optional) – If set to True, the layer will cache the computation of \(\mathbf{\hat{D}}^{-1} \mathbf{\hat{A}}\) on first execution, and will use the cached version for further executions. This parameter should only be set to True in transductive learning scenarios. (default: False)

  • add_self_loops (bool, optional) – If set to False, will not add self-loops to the input graph. (default: True)

  • normalize (bool, optional) – Whether to add self-loops and compute symmetric normalization coefficients on the fly. (default: True)

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

fill_value = 0.5
cached = False
add_self_loops = True
normalize = True
reset_parameters()
forward(x: torch.Tensor, edge_index: torch_geometric.typing.Adj, edge_weight: torch_geometric.typing.OptTensor = None) → torch.Tensor
message(x_j: torch.Tensor, edge_weight: torch_geometric.typing.OptTensor) → torch.Tensor