torch_geometric.datasets.GNNBenchmarkDataset

class GNNBenchmarkDataset(root: str, name: str, split: str = 'train', transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, pre_filter: Optional[Callable] = None, force_reload: bool = False)[source]

Bases: InMemoryDataset

A variety of artificially and semi-artificially generated graph datasets from the “Benchmarking Graph Neural Networks” paper.

Note

The ZINC dataset is provided via torch_geometric.datasets.ZINC.

Parameters:

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

  • name (str) – The name of the dataset (one of "PATTERN", "CLUSTER", "MNIST", "CIFAR10", "TSP", "CSL")

  • split (str, optional) – If "train", loads the training dataset. If "val", loads the validation dataset. If "test", loads the test dataset. (default: "train")

  • 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)

  • pre_filter (callable, optional) – A function that takes in an torch_geometric.data.Data object and returns a boolean value, indicating whether the data object should be included in the final dataset. (default: None)

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

STATS:

Name

#graphs

#nodes

#edges

#features

#classes

PATTERN

10,000

~118.9

~6,098.9

3

2

CLUSTER

10,000

~117.2

~4,303.9

7

6

MNIST

55,000

~70.6

~564.5

3

10

CIFAR10

45,000

~117.6

~941.2

5

10

TSP

10,000

~275.4

~6,885.0

2

2

CSL

150

~41.0

~164.0

0

10