torch_geometric.datasets.IGMCDataset

class IGMCDataset(root: str, name: str, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None)[source]

Bases: InMemoryDataset

The user-item heterogeneous rating datasets "Douban", "Flixster" and "Yahoo-Music" from the “Inductive Matrix Completion Based on Graph Neural Networks” paper.

Nodes represent users and items. Edges and features between users and items represent a (training) rating of the item given by the user.

Parameters

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

  • name (str) – The name of the dataset ("Douban", "Flixster", "Yahoo-Music").

  • transform (callable, optional) – A function/transform that takes in an torch_geometric.data.HeteroData 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.HeteroData object and returns a transformed version. The data object will be transformed before being saved to disk. (default: None)