- class FB15k_237(root: str, split: str = 'train', transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None)
The FB15K237 dataset from the “Translating Embeddings for Modeling Multi-Relational Data” paper, containing 14,541 entities, 237 relations and 310,116 fact triples.
FB15kdataset suffers from major test leakage through inverse relations, where a large number of test triples could be obtained by inverting triples in the training set. In order to create a dataset without this characteristic, the
FB15k_237describes a subset of
FB15kwhere inverse relations are removed.
root (str) – Root directory where the dataset should be saved.
split (str, optional) – If
"train", loads the training dataset. If
"val", loads the validation dataset. If
"test", loads the test dataset. (default:
transform (callable, optional) – A function/transform that takes in an
torch_geometric.data.Dataobject and returns a transformed version. The data object will be transformed before every access. (default:
pre_transform (callable, optional) – A function/transform that takes in an
torch_geometric.data.Dataobject and returns a transformed version. The data object will be transformed before being saved to disk. (default: