torch_geometric.datasets.BAShapes

class BAShapes(connection_distribution: str = 'random', transform: Optional[Callable] = None)

Bases: BAShapes

The BA-Shapes dataset from the “GNNExplainer: Generating Explanations for Graph Neural Networks” paper, containing a Barabasi-Albert (BA) graph with 300 nodes and a set of 80 “house”-structured graphs connected to it.

Warning

BAShapes is deprecated and will be removed in a future release. Use ExplainerDataset in combination with torch_geometric.datasets.graph_generator.BAGraph instead.

Parameters

  • connection_distribution (str, optional) – Specifies how the houses and the BA graph get connected. Valid inputs are "random" (random BA graph nodes are selected for connection to the houses), and "uniform" (uniformly distributed BA graph nodes are selected for connection to the houses). (default: "random")

  • 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)