torch_geometric.datasets.RelLinkPredDataset

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

Bases: InMemoryDataset

The relational link prediction datasets from the “Modeling Relational Data with Graph Convolutional Networks” paper. Training and test splits are given by sets of triplets.

Parameters:

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

  • name (str) – The name of the dataset ("FB15k-237").

  • 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:

#nodes

#edges

#features

#classes

14,541

544,230

0

0