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

异质图 "Roman-empire", "Amazon-ratings", "Minesweeper", "Tolokers" 和 "Questions" 来自论文 “A Critical Look at the Evaluation of GNNs under Heterophily: Are We Really Making Progress?”。

Parameters:

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

  • name (str) – 数据集的名称 ("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)

统计:

名称

#节点

#edges

#特性

#classes

罗马帝国

22,662

32,927

300

18

亚马逊评分

24,492

93,050

300

5

扫雷

10,000

39,402

7

2

托洛克斯

11,758

519,000

10

2

问题

48,921

153,540

301

2