torch_geometric.datasets.BA2MotifDataset

class BA2MotifDataset(root: str, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, force_reload: bool = False)

Bases: InMemoryDataset

用于评估可解释性算法的合成BA-2motifs图分类数据集，如“Parameterized Explainer for Graph Neural Network”论文中所述。 BA2MotifDataset包含1000个随机的Barabasi-Albert（BA）图。 其中一半的图附加了一个HouseMotif，其余的图附加了一个五节点的CycleMotif。 根据附加的motif类型，这些图被分配到两个类别中的一个。

该数据集是从官方实现中预先计算得出的。如果你想创建自己的变体，可以使用ExplainerDataset：

import torch
from torch_geometric.datasets import ExplainerDataset
from torch_geometric.datasets.graph_generator import BAGraph
from torch_geometric.datasets.motif_generator import HouseMotif
from torch_geometric.datasets.motif_generator import CycleMotif

dataset1 = ExplainerDataset(
    graph_generator=BAGraph(num_nodes=25, num_edges=1),
    motif_generator=HouseMotif(),
    num_motifs=1,
    num_graphs=500,
)

dataset2 = ExplainerDataset(
    graph_generator=BAGraph(num_nodes=25, num_edges=1),
    motif_generator=CycleMotif(5),
    num_motifs=1,
    num_graphs=500,
)

dataset = torch.utils.data.ConcatDataset([dataset1, dataset2])

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:

#图表	#节点	#edges	#特性	#classes
1000	25	~51.0	10	2