torch_geometric.datasets.WebKB

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

Bases: InMemoryDataset

在“Geom-GCN: Geometric Graph Convolutional Networks”论文中使用的WebKB数据集。 节点代表网页，边代表它们之间的超链接。 节点特征是网页的词袋表示。 任务是将节点分类为五个类别之一：学生、项目、课程、员工和教职员工。

Parameters:

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

  • name (str) – 数据集的名称 ("Cornell", "Texas", "Wisconsin").

  • 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

康奈尔

183

298

1,703

5

德克萨斯

183

325

1,703

5

威斯康星州

251

515

1,703

5