torch_geometric.datasets.HeterophilousGraphDataset

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

Bases: InMemoryDataset

The heterophilous graphs "Roman-empire", "Amazon-ratings", "Minesweeper", "Tolokers" and "Questions" from the “A Critical Look at the Evaluation of GNNs under Heterophily: Are We Really Making Progress?” paper.

Parameters:

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

  • name (str) – The name of the dataset ("Roman-empire", "Amazon-ratings", "Minesweeper", "Tolokers", "Questions").

  • 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

Roman-empire

22,662

32,927

300

18

Amazon-ratings

24,492

93,050

300

5

Minesweeper

10,000

39,402

7

2

Tolokers

11,758

519,000

10

2

Questions

48,921

153,540

301

2