Functions — github.com/AaltoPML/Rethinking-pooling-in-GNNs

CodeHub MCPcopy Create free account

hub / github.com/AaltoPML/Rethinking-pooling-in-GNNs / functions

Functions83 in github.com/AaltoPML/Rethinking-pooling-in-GNNs

⨍ Functions 83 ◇ Types & classes 16

↓ 8 callersFunctionevaluate

(model, loader, device, evaluator=None)

gmn/train.py:45

↓ 5 callersFunctionfetch_assign_matrix

(random, dim1, dim2, normalize=False)

↓ 4 callersFunctionget_data

(name, batch_size, rwr=False, cleaned=False)

data/datasets.py:45

↓ 4 callersFunctionget_params

gmn/params.py:1

↓ 4 callersFunctiongraph_permutation

↓ 4 callersFunctionset_seed

↓ 4 callersFunctiontrain

(model, optimizer, loader, device)

↓ 3 callersMethodbn

diffpool/diffpool_v2.py:35

↓ 2 callersMethod__init__

(self, num_features, num_classes, max_num_nodes, num_layers, gnn_hidden_dim, gnn_output_dim,

diffpool/diffpool_v2.py:98

↓ 2 callersMethod__init__

(self, num_features, num_classes, max_num_nodes, num_layers, gnn_hidden_dim, gnn_output_dim,

diffpool/diffpool.py:93

↓ 2 callersFunction_rank3_trace

mincut/mincut_pool_mod.py:96

↓ 2 callersFunctiondense_mincut_pool

r"""MinCUt pooling operator from the `"Mincut Pooling in Graph Neural Networks" <https://arxiv.org/abs/1907.00481>`_ paper .. math::

mincut/mincut_pool_mod.py:6

↓ 1 callersMethodKL_reg

↓ 1 callersMethod__init__

(self, num_feats, max_nodes, num_classes, num_heads, hidden_dim, num_keys, mem_hidden_dim=100

↓ 1 callersFunction_rank3_diag

mincut/mincut_pool_mod.py:100

↓ 1 callersFunctionbatched_negative_edges

r"""Samples random negative edges of multiple graphs given by :attr:`edge_index` and :attr:`batch`. Args: edge_index (LongTensor): Th

graclus/negative_edges.py:74

↓ 1 callersFunctiondata_split

data/datasets.py:104

↓ 1 callersFunctionget_mod_zinc

data/datasets.py:133

↓ 1 callersFunctionget_molhiv

data/datasets.py:79

↓ 1 callersFunctionget_smnist

data/datasets.py:118

↓ 1 callersFunctionget_tudataset

(name, rwr, cleaned=False)

data/datasets.py:87

↓ 1 callersMethodinitial_query

(self, x, edge_index, edge_attr=None)

↓ 1 callersFunctionkl_train

(model, optimizer, loader, device)

gmn/train.py:25

↓ 1 callersFunctionnegative_edges

r"""Samples random negative edges of a graph given by :attr:`edge_index`. Args: edge_index (LongTensor): The edge indices. num_no

graclus/negative_edges.py:9

data/datasets.py:20

data/datasets.py:28

data/datasets.py:38

(self, emb_dim, aggr)

(self, in_channels, hidden_channels, out_channels,

diffpool/diffpool_v2.py:16

(self, dim_input, dim_hidden, dim_embedding, current_num_clusters, no_new_clusters, pooling_t

diffpool/diffpool_v2.py:62

(self, num_layers, in_channels, out_channels, residual=True

diffpool/diffpool.py:16

(self, dim_input, dim_embedding, current_num_clusters, no_new_clusters, pooling_type, invaria

diffpool/diffpool.py:55

(self, max_nodes)

data/datasets.py:17

data/datasets.py:25

(self, mean, std)

data/datasets.py:34

(self, root, train=True, transform=None, p

data/smnist.py:12

(self, root, split='train', transform=None,

data/mod_zinc.py:12

(self, num_features, heads, num_keys, dim_out, key_std=10, variant='gmn', max_queries=100)

(self, num_features, num_classes, max_num_nodes, hidden, pooling_type, num_layers, encode_edg

mincut/mincutpool.py:16

(self, num_features, num_classes, num_layers, hidden, pooling_type, no_cat=False, encode_edge

graclus/graclus.py:12

data/smnist.py:31

data/mod_zinc.py:36

Functioneval_regression

(model, loader, device)

gmn/train.py:112

Functionevaluate

(model, loader, device, perm=False, evaluator=None)

diffpool/train.py:28

Functionevaluate

(model, loader, device, perm=False, evaluator=None)

mincut/train.py:28

Functionevaluate

(model, loader, device, evaluator=None)

graclus/train.py:21

Functionevaluate_regression

(model, loader, device, perm=False, evaluator=None)

diffpool/train.py:79

Functionevaluate_regression

(model, loader, device, perm=False)

mincut/train.py:80

Functionevaluate_regression

(model, loader, device, evaluator=None)

graclus/train.py:62

(self, x, edge_index, edge_attr)

(self, x, adj, mask=None)

diffpool/diffpool_v2.py:43

(self, x, adj, mask=None)

diffpool/diffpool_v2.py:77

diffpool/diffpool_v2.py:145

(self, x, adj, mask=None)

diffpool/diffpool.py:38

(self, x, adj, mask=None)

diffpool/diffpool.py:72

diffpool/diffpool.py:144

(self, Q, mask, tau=1.0)

(self, x, edge_index, batch, edge_attr)

mincut/mincutpool.py:49

graclus/graclus.py:43

Functionget_params

diffpool/params.py:1

Functionget_params

diffpool/params_v2.py:1

Functionget_params

mincut/params.py:1

Functionget_params

graclus/params.py:1

Functionkl_train_regression

(model, optimizer, loader, device)

gmn/train.py:93

Functionknn_filter

(self, x_j, edge_attr)

data/smnist.py:36

data/mod_zinc.py:41

Methodprocessed_file_names

data/smnist.py:28

Methodprocessed_file_names

data/mod_zinc.py:33

Methodraw_file_names

data/smnist.py:24

Methodraw_file_names

data/mod_zinc.py:29

Methodreset_parameters

graclus/graclus.py:35

Functionrwr_filter

(model, optimizer, loader, linkpred, device)

diffpool/train.py:6

(model, optimizer, loader, device)

mincut/train.py:6

(model, optimizer, loader, device)

graclus/train.py:5

Functiontrain_regression

(model, optimizer, loader, linkpred, device)

diffpool/train.py:58

Functiontrain_regression

(model, optimizer, loader, device)

gmn/train.py:74

Functiontrain_regression

(model, optimizer, loader, device)

mincut/train.py:59

Functiontrain_regression

(model, optimizer, loader, device)

graclus/train.py:47

(self, aggr_out)