cogdl.models
¶
Subpackages¶
cogdl.models.emb
cogdl.models.emb.complex
cogdl.models.emb.deepwalk
cogdl.models.emb.dgk
cogdl.models.emb.distmult
cogdl.models.emb.dngr
cogdl.models.emb.gatne
cogdl.models.emb.graph2vec
cogdl.models.emb.grarep
cogdl.models.emb.hin2vec
cogdl.models.emb.hope
cogdl.models.emb.knowledge_base
cogdl.models.emb.line
cogdl.models.emb.metapath2vec
cogdl.models.emb.netmf
cogdl.models.emb.netsmf
cogdl.models.emb.node2vec
cogdl.models.emb.prone
cogdl.models.emb.pte
cogdl.models.emb.rotate
cogdl.models.emb.sdne
cogdl.models.emb.spectral
cogdl.models.emb.transe
cogdl.models.nn
cogdl.models.nn.asgcn
cogdl.models.nn.compgcn
cogdl.models.nn.dgi
cogdl.models.nn.dgl_gcc
cogdl.models.nn.disengcn
cogdl.models.nn.fastgcn
cogdl.models.nn.gat
cogdl.models.nn.gcn
cogdl.models.nn.gcnii
cogdl.models.nn.graphsage
cogdl.models.nn.mixhop
cogdl.models.nn.mlp
cogdl.models.nn.mvgrl
cogdl.models.nn.patchy_san
cogdl.models.nn.pyg_cheb
cogdl.models.nn.pyg_deepergcn
cogdl.models.nn.pyg_dgcnn
cogdl.models.nn.pyg_diffpool
cogdl.models.nn.pyg_drgat
cogdl.models.nn.pyg_drgcn
cogdl.models.nn.pyg_gat
cogdl.models.nn.pyg_gcn
cogdl.models.nn.pyg_gcnmix
cogdl.models.nn.pyg_gin
cogdl.models.nn.pyg_gpt_gnn
cogdl.models.nn.pyg_grand
cogdl.models.nn.pyg_gtn
cogdl.models.nn.pyg_han
cogdl.models.nn.pyg_infograph
cogdl.models.nn.pyg_infomax
cogdl.models.nn.pyg_sortpool
cogdl.models.nn.pyg_srgcn
cogdl.models.nn.pyg_stpgnn
cogdl.models.nn.pyg_unet
cogdl.models.nn.pyg_unsup_graphsage
cogdl.models.nn.rgcn
Package Contents¶
Functions¶
|
New model types can be added to cogdl with the |
|
Compute utility lists for non-uniform sampling from discrete distributions. |
|
Draw sample from a non-uniform discrete distribution using alias sampling. |
|
-
class
cogdl.models.
BaseModel
[source]¶ Bases:
torch.nn.Module
-
static
add_args
(parser)¶ Add model-specific arguments to the parser.
-
abstract classmethod
build_model_from_args
(cls, args)¶ Build a new model instance.
-
static
get_trainer
(taskType: Any, args: Any) → Optional[Type[BaseTrainer]]¶
-
static
-
cogdl.models.
register_model
(name)[source]¶ New model types can be added to cogdl with the
register_model()
function decorator.For example:
@register_model('gat') class GAT(BaseModel): (...)
- Args:
name (str): the name of the model
-
cogdl.models.
alias_setup
(probs)[source]¶ Compute utility lists for non-uniform sampling from discrete distributions. Refer to https://hips.seas.harvard.edu/blog/2013/03/03/the-alias-method-efficient-sampling-with-many-discrete-outcomes/ for details