Functions — github.com/Graph-and-Geometric-Learning/hyperbolic-transformer

hub / github.com/Graph-and-Geometric-Learning/hyperbolic-transformer / functions

Functions650 in github.com/Graph-and-Geometric-Learning/hyperbolic-transformer

⨍ Functions 650◇ Types & classes 92

↓ 1 callersFunctionparse_args

()

large/main-batch.py:34

↓ 1 callersFunctionparse_method

(args, device)

medium/parse.py:4

↓ 1 callersFunctionparser_add_main_args

(parser)

medium/parse.py:12

↓ 1 callersFunctionprepare_batch_data

(i, args, dataset, idx, n, train_mask, true_label, degrees, device)

large/main-batch.py:219

↓ 1 callersFunctionpreprocess_features

Row-normalize feature matrix and convert to tuple representation

large/dataset.py:600

↓ 1 callersFunctionpreprocess_features

Row-normalize feature matrix and convert to tuple representation

medium/dataset.py:265

↓ 1 callersFunctionpreprocess_graph

(dataset, args, n)

large/main.py:121

↓ 1 callersFunctionpreprocess_graph

(dataset, args)

large/main-batch.py:139

↓ 1 callersFunctionprint_dataset_info

(dataset)

large/main.py:85

↓ 1 callersFunctionprint_dataset_info

(dataset)

large/main-batch.py:83

↓ 1 callersMethodproju

Project a tangent vector onto the tangent space at a point. Parameters: x (torch.Tensor): Point on the manifold.

large/manifolds/lorentz.py:224

↓ 1 callersMethodproju

Project a tangent vector onto the tangent space at a point. Parameters: x (torch.Tensor): Point on the manifold.

medium/manifolds/lorentz.py:187

↓ 1 callersMethodproju

Project a tangent vector onto the tangent space at a point. Parameters: x (torch.Tensor): Point on the manifold.

Hypformer/manifolds/lorentz.py:204

↓ 1 callersFunctionrand_train_test_idx

randomly splits label into train/valid/test splits

medium/data_utils.py:12

↓ 1 callersMethodrandom_normal

Create a random point on the manifold, induced by a normal distribution on the tangent space of zero. Parameters: size:

large/manifolds/lorentz.py:492

↓ 1 callersMethodrandom_normal

r""" Create a point on the manifold, measure is induced by Normal distribution on the tangent space of zero. Parameters -----

medium/manifolds/lorentz.py:443

↓ 1 callersMethodreset_parameters

Reset layer parameters.

large/manifolds/layer.py:28

↓ 1 callersMethodreset_parameters

(self)

medium/gnns.py:211

↓ 1 callersMethodreset_parameters

(self)

medium/gnns.py:771

↓ 1 callersMethodreset_parameters

(self)

medium/manifolds/hyp_layer.py:20

↓ 1 callersMethodreset_parameters

(self)

Hypformer/manifolds/hyp_layer.py:23

↓ 1 callersMethodreset_parameters

Reset layer parameters.

Hypformer/manifolds/layer.py:28

↓ 1 callersFunctionsabs

(x, eps: float = 1e-15)

large/manifolds/utils.py:83

↓ 1 callersFunctionsabs

(x, eps: float = 1e-15)

medium/manifolds/manifold_utils.py:84

↓ 1 callersFunctionsabs

(x, eps: float = 1e-15)

Hypformer/manifolds/utils.py:83

↓ 1 callersFunctionselect_eval_function

(args)

large/main.py:154

↓ 1 callersFunctionselect_eval_function

(args)

large/main-batch.py:125

↓ 1 callersFunctionselect_loss_function

(args)

large/main.py:144

↓ 1 callersFunctionselect_loss_function

(args)

large/main-batch.py:114

↓ 1 callersFunctionsign

(x)

large/manifolds/utils.py:79

↓ 1 callersFunctionsign

(x)

medium/manifolds/manifold_utils.py:79

↓ 1 callersFunctionsign

(x)

Hypformer/manifolds/utils.py:79

↓ 1 callersFunctionsize2shape

(*size: Union[Tuple[int], int])

large/manifolds/utils.py:141

↓ 1 callersFunctionsize2shape

(*size: Union[Tuple[int], int])

medium/manifolds/manifold_utils.py:142

↓ 1 callersFunctionsize2shape

(*size: Union[Tuple[int], int])

Hypformer/manifolds/utils.py:141

↓ 1 callersFunctionsqrt

(x: torch.Tensor)

Hypformer/manifolds/utils.py:217

↓ 1 callersMethodstep

(self)

medium/manifolds/hyp_layer.py:203

↓ 1 callersFunctionstrip_tuple

(tup: Tuple)

large/manifolds/utils.py:59

↓ 1 callersFunctionstrip_tuple

(tup: Tuple)

medium/manifolds/manifold_utils.py:59

↓ 1 callersFunctionstrip_tuple

(tup: Tuple)

Hypformer/manifolds/utils.py:59

↓ 1 callersFunctionto_sparse_tensor

converts the edge_index into SparseTensor

large/data_utils.py:153

↓ 1 callersFunctiontrain_and_evaluate

(args, dataset, split_idx_lst, device, criterion, eval_func)

large/main.py:167

↓ 1 callersFunctiontrain_and_evaluate

(args, dataset, split_idx_lst, device, criterion, eval_func)

large/main-batch.py:164

↓ 1 callersFunctiontrain_one_epoch

(epoch, args, dataset, device, model, optimizer, criterion, train_idx)

large/main.py:201

↓ 1 callersFunctiontrain_one_epoch

(epoch, args, dataset, device, model, optimizer, criterion, n, train_mask, true_label, degrees, threshold,

large/main-batch.py:196

↓ 1 callersMethodtransp

Perform parallel transport of a tangent vector. Parameters: x (torch.Tensor): Starting point on the manifold.

large/manifolds/lorentz.py:389

↓ 1 callersMethodtransp

Perform parallel transport of a tangent vector. Parameters: x (torch.Tensor): Starting point on the manifold.

medium/manifolds/lorentz.py:351

↓ 1 callersMethodtransp

Perform parallel transport of a tangent vector. Parameters: x (torch.Tensor): Starting point on the manifold.

Hypformer/manifolds/lorentz.py:359

↓ 1 callersMethodtransp0

Perform parallel transport from the origin. Parameters: y (torch.Tensor): Ending point on the manifold. u (t

large/manifolds/lorentz.py:404

↓ 1 callersMethodtransp0

(self, y: torch.Tensor, u: torch.Tensor, *, dim=-1)

medium/manifolds/lorentz.py:366

↓ 1 callersMethodtransp0

Perform parallel transport from the origin. Parameters: y (torch.Tensor): Ending point on the manifold. u (t

Hypformer/manifolds/lorentz.py:374

↓ 1 callersMethodzero_grad

(self)

medium/manifolds/hyp_layer.py:208

(self, num_nodes, out_channels)

large/gnns.py:15

Method__init__

takes 'hops' power of the normalized adjacency

large/gnns.py:69

Method__init__

self-implementation of SGC

large/gnns.py:83

Method__init__

(self, in_channels, hidden_channels, out_channels, hops, num_layers, dropout, use_bn=False)

large/gnns.py:131

Method__init__

(self, in_channels, hidden_channels, out_channels, num_layers=2, dropout=0.5, save_mem=True,

large/gnns.py:178

Method__init__

(self, in_channels, hidden_channels, out_channels, hops, num_layers, dropout, use_bn=False)

large/gnns.py:223

Method__init__

(self, in_channels, hidden_channels, out_channels, num_layers=2, dropout=0.5, use_bn=False, h

large/gnns.py:273

Method__init__

(self, out_channels, alpha, hops, num_iters=50, mult_bin=False)

large/gnns.py:315

Method__init__

(self, in_channels, out_channels, hops=2)

large/gnns.py:367

Method__init__

(self, in_channels, hidden_channels, out_channels, num_layers=2, dropout=0.5, hops=2)

large/gnns.py:395

Method__init__

(self, in_channels, hidden_channels, out_channels, num_layers=2, dropout=0.5, save_mem=False,

large/gnns.py:453

Method__init__

(self, in_channels, hidden_channels, out_channels, num_layers=2, dropout=0.5, heads=2, jk_typ

(self, in_channels, hidden_channels, out_channels, dropout=.5, K=10, alpha=.1)

large/gnns.py:569

Method__init__

(self, K, alpha, Init, Gamma=None, bias=True, **kwargs)

large/gnns.py:594

Method__init__

(self, in_channels, hidden_channels, out_channels, Init='PPR', dprate=.5, dropout=.5, K=10, alpha=.1, Gamma=No

large/gnns.py:657

Method__init__

(self, in_channels, out_channels, use_weight=True, use_init=False)

large/gnns.py:692

Method__init__

(self, in_channels, hidden_channels, num_layers=2, dropout=0.5, use_bn=True, use_residual=True,

large/gnns.py:727

Method__init__

based off of ogb NodePropPredDataset https://github.com/snap-stanford/ogb/blob/master/ogb/nodeproppred/dataset.py Gives torch

large/dataset.py:29

Method__init__

(self, runs, args=None)

large/logger.py:14

Method__init__

Initializes a TransConvLayer instance. Args: manifold: The manifold to use for the layer. in_channels: The n

large/hypformer.py:16

Method__init__

(self, in_channels, hidden_channels, out_channels, trans_num_layers=1, trans_num_heads=1, tra

large/hypformer.py:268

Method__init__

Initialize a Lorentz manifold with k, curvature is -1/k. Parameters: k (float): Curvature parameter of the manifold.

large/manifolds/lorentz.py:10

Method__init__

(self, manifold, in_features, manifold_out=None)

large/manifolds/layer.py:20

Method__init__

(self, manifold, manifold_out=None)

large/manifolds/layer.py:53

Method__init__

(self, manifold, activation, manifold_out=None)

large/manifolds/layer.py:79

Method__init__

(self, manifold, dropout, manifold_out=None)

large/manifolds/layer.py:106

Method__init__

(self, manifold, in_features, out_features, bias=True, dropout=0.0, manifold_out=None)

large/manifolds/layer.py:137

Method__init__

(self, model, args)

large/manifolds/layer.py:221

Method__init__

(self, num_nodes, out_channels)

medium/gnns.py:18

Method__init__

takes 'hops' power of the normalized adjacency

medium/gnns.py:74

Method__init__

self-implementation of SGC

medium/gnns.py:88

Method__init__

(self, in_channels, hidden_channels, out_channels, hops, num_layers, dropout, use_bn=False)

medium/gnns.py:137

Method__init__

(self, in_channels, hidden_channels, out_channels, num_layers=2, dropout=0.5, save_mem=True,

medium/gnns.py:183

Method__init__

(self, in_channels, hidden_channels, out_channels, hops, num_layers, dropout, use_bn=False)

medium/gnns.py:229

Method__init__

(self, in_channels, hidden_channels, out_channels, num_layers=2, dropout=0.5, use_bn=False, h

medium/gnns.py:280

Method__init__

(self, out_channels, alpha, hops, num_iters=50, mult_bin=False)

medium/gnns.py:323

Method__init__

(self, in_channels, out_channels, hops=2)

medium/gnns.py:376

Method__init__

(self, in_channels, hidden_channels, out_channels, num_layers=2, dropout=0.5, hops=2)

medium/gnns.py:406

Method__init__

(self, in_channels, hidden_channels, out_channels, num_layers=2, dropout=0.5, save_mem=False,

medium/gnns.py:464

Method__init__

(self, in_channels, hidden_channels, out_channels, num_layers=2, dropout=0.5, heads=2, jk_typ

(self, in_channels, hidden_channels, out_channels, dropout=.5, K=10, alpha=.1)

medium/gnns.py:580

Method__init__

(self, K, alpha, Init, Gamma=None, bias=True, **kwargs)

medium/gnns.py:606

Method__init__

(self, in_channels, hidden_channels, out_channels, Init='PPR', dprate=.5, dropout=.5, K=10, alpha=.1,

medium/gnns.py:669

Method__init__

(self, in_channels, out_channels, use_weight=True, use_init=False)

medium/gnns.py:706

← previous next →201–300 of 650, ranked by callers