torch_geometric.datasets.CitationFull

class CitationFull(root: str, name: str, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, to_undirected: bool = True)[source]

Bases: InMemoryDataset

The full citation network datasets from the “Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking” paper. Nodes represent documents and edges represent citation links. Datasets include "Cora", "Cora_ML", "CiteSeer", "DBLP", "PubMed".

Parameters

  • root (str) – Root directory where the dataset should be saved.

  • name (str) – The name of the dataset ("Cora", "Cora_ML" "CiteSeer", "DBLP", "PubMed").

  • transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before every access. (default: None)

  • pre_transform (callable, optional) – A function/transform that takes in an torch_geometric.data.Data object and returns a transformed version. The data object will be transformed before being saved to disk. (default: None)

  • to_undirected (bool, optional) – Whether the original graph is converted to an undirected one. (default: True)

STATS:

Name

#nodes

#edges

#features

#classes

Cora

19,793

126,842

8,710

70

Cora_ML

2,995

16,316

2,879

7

CiteSeer

4,230

10,674

602

6

DBLP

17,716

105,734

1,639

4

PubMed

19,717

88,648

500

3