torch_geometric.datasets.NELL

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

Bases: InMemoryDataset

NELL数据集，来自 “Toward an Architecture for Never-Ending Language Learning” 论文的知识图谱。 该数据集的处理方式与 “Revisiting Semi-Supervised Learning with Graph Embeddings” 论文中描述的一致。

注意

实体节点由类型为torch.sparse_csr_tensor的稀疏特征向量描述。

Parameters:

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

  • 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:

#节点

#edges

#特性

#classes

65,755

251,550

61,278

186