torch_geometric.nn.conv.SplineConv
- class SplineConv(in_channels: Union[int, Tuple[int, int]], out_channels: int, dim: int, kernel_size: Union[int, List[int]], is_open_spline: bool = True, degree: int = 1, aggr: str = 'mean', root_weight: bool = True, bias: bool = True, **kwargs)[source]
Bases:
MessagePassing
The spline-based convolutional operator from the “SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels” paper.
\[\mathbf{x}^{\prime}_i = \frac{1}{|\mathcal{N}(i)|} \sum_{j \in \mathcal{N}(i)} \mathbf{x}_j \cdot h_{\mathbf{\Theta}}(\mathbf{e}_{i,j}),\]where \(h_{\mathbf{\Theta}}\) denotes a kernel function defined over the weighted B-Spline tensor product basis.
Note
Pseudo-coordinates must lay in the fixed interval \([0, 1]\) for this method to work as intended.
- Parameters:
in_channels (int or tuple) – Size of each input sample, or
-1
to derive the size from the first input(s) to the forward method. A tuple corresponds to the sizes of source and target dimensionalities.out_channels (int) – Size of each output sample.
dim (int) – Pseudo-coordinate dimensionality.
is_open_spline (bool or [bool], optional) – If set to
False
, the operator will use a closed B-spline basis in this dimension. (defaultTrue
)degree (int, optional) – B-spline basis degrees. (default:
1
)aggr (str, optional) – The aggregation scheme to use (
"add"
,"mean"
,"max"
). (default:"mean"
)root_weight (bool, optional) – If set to
False
, the layer will not add transformed root node features to the output. (default:True
)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
.