torch_geometric.datasets.DGraphFin

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

Bases: InMemoryDataset

The DGraphFin networks from the “DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detection” paper. It is a directed, unweighted dynamic graph consisting of millions of nodes and edges, representing a realistic user-to-user social network in financial industry. Node represents a Finvolution user, and an edge from one user to another means that the user regards the other user as the emergency contact person. Each edge is associated with a timestamp ranging from 1 to 821 and a type of emergency contact ranging from 0 to 11.

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)

STATS:

#nodes

#edges

#features

#classes

3,700,550

4,300,999

17

2