pyagc.transforms.RandomDropEdge

class RandomDropEdge(p: float = 0.5, edge_attrs: Optional[List[str]] = ['edge_attr'], inplace: bool = False)[source]

Randomly drops edges in the graph (functional name: random_drop_edge), as described in the “DropEdge: Towards Deep Graph Convolutional Networks on Node Classification” paper. Optionally, drops associated edge attributes.

Parameters:

p (float, optional) – The probability of dropping each edge. Must be between 0 and 1. Default is 0.5.
edge_attrs (List[str], optional) – The names of edge attributes to drop alongside dropped edges. Default is ["edge_attr"].
inplace (bool, optional) – If set to False, will clone the input data before applying the transform. Default is False.

__init__(p: float = 0.5, edge_attrs: Optional[List[str]] = ['edge_attr'], inplace: bool = False)[source]

Methods

__init__([p, edge_attrs, inplace])