torch_geometric.datasets.Entities

class Entities(root: str, name: str, hetero: bool = False, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, force_reload: bool = False)[source]

Bases: InMemoryDataset

The relational entities networks "AIFB", "MUTAG", "BGS" and "AM" from the “Modeling Relational Data with Graph Convolutional Networks” paper. Training and test splits are given by node indices.

Parameters:

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

  • name (str) – The name of the dataset ("AIFB", "MUTAG", "BGS", "AM").

  • hetero (bool, optional) – If set to True, will save the dataset as a HeteroData object. (default: False)

  • 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)

  • force_reload (bool, optional) – Whether to re-process the dataset. (default: False)

STATS:

Name

#nodes

#edges

#features

#classes

AIFB

8,285

58,086

0

4

AM

1,666,764

11,976,642

0

11

MUTAG

23,644

148,454

0

2

BGS

333,845

1,832,398

0

2