nip.graph_isomorphism.dataset_generation.generate_er_graphs

nip.graph_isomorphism.dataset_generation.generate_er_graphs#

nip.graph_isomorphism.dataset_generation.generate_er_graphs(num_graphs: int, graph_size: int, edge_probability: float, device: device | str | int = 'cpu') → Int32[Tensor, 'batch node1 node2'][source]#

Generate a batch of Erdős-Rényi graphs.

Parameters:

  • num_graphs (int) – The number of graphs to generate.

  • graph_size (int) – The number of nodes in each graph.

  • edge_probability (float) – The probability of an edge between two nodes.

  • device (TorchDevice, default="cpu") – The device to use for the computation.

Returns:

adjacency (Int32[Tensor, “batch node1 node2”]) – The batch of adjacency matrices for the generated graphs.