models.nn.patchy_san
¶
Module Contents¶
Functions¶
|
assemble neighbors for node with BFS strategy |
|
|
|
1-dimension Wl method used for node normalization for all the subgraphs |
|
construct features for cnn |
|
construct features |
-
class
models.nn.patchy_san.
PatchySAN
(batch_size, num_features, num_classes, num_sample, stride, num_neighbor, iteration)[source]¶ Bases:
models.BaseModel
The Patchy-SAN model from the “Learning Convolutional Neural Networks for Graphs” paper.
- Args:
batch_size (int) : The batch size of training. sample (int) : Number of chosen vertexes. stride (int) : Node selection stride. neighbor (int) : The number of neighbor for each node. iteration (int) : The number of training iteration.
-
models.nn.patchy_san.
assemble_neighbor
(G, node, num_neighbor, sorted_nodes)[source]¶ assemble neighbors for node with BFS strategy
-
models.nn.patchy_san.
one_dim_wl
(graph_list, init_labels, iteration=5)[source]¶ 1-dimension Wl method used for node normalization for all the subgraphs