cogdl.models.nn.pyg_sortpool

Module Contents

Classes

SortPool

Implimentation of sortpooling in paper `”An End-to-End Deep Learning

Functions

scatter_sum(src, index, dim, dim_size)

spare2dense_batch(x, batch=None, fill_value=0)

cogdl.models.nn.pyg_sortpool.scatter_sum(src, index, dim, dim_size)[source]
cogdl.models.nn.pyg_sortpool.spare2dense_batch(x, batch=None, fill_value=0)[source]
class cogdl.models.nn.pyg_sortpool.SortPool(in_feats, hidden_dim, num_classes, num_layers, out_channel, kernel_size, k=30, dropout=0.5)[source]

Bases: cogdl.models.BaseModel

Implimentation of sortpooling in paper “An End-to-End Deep Learning Architecture for Graph Classification” <https://www.cse.wustl.edu/~muhan/papers/AAAI_2018_DGCNN.pdf>__.

in_featsint

Size of each input sample.

out_featsint

Size of each output sample.

hidden_dimint

Dimension of hidden layer embedding.

num_classesint

Number of target classes.

num_layersint

Number of graph neural network layers before pooling.

kint, optional

Number of selected features to sort, default: 30.

out_channelint

Number of the first convolution’s output channels.

kernel_sizeint

Size of the first convolution’s kernel.

dropoutfloat, optional

Size of dropout, default: 0.5.

static add_args(parser)[source]

Add model-specific arguments to the parser.

classmethod build_model_from_args(cls, args)[source]

Build a new model instance.

classmethod split_dataset(cls, dataset, args)[source]
forward(self, batch)[source]