dgl.graphbolt.add_reverse_edges

dgl.graphbolt.add_reverse_edges(edges: Dict[str, Tensor] | Tensor, reverse_etypes_mapping: Dict[str, str] | None = None)[source]

This function finds the reverse edges of the given edges and returns the composition of them. In a homogeneous graph, reverse edges have inverted source and destination node IDs. While in a heterogeneous graph, reversing also involves swapping node IDs and their types. This function could be used before exclude_edges function to help find targeting edges. Note: The found reverse edges may not really exists in the original graph. And repeat edges could be added becasue reverse edges may already exists in the edges.

Parameters:

  • edges (Union[Dict[str, torch.Tensor], torch.Tensor]) –

    • If sampled subgraph is homogeneous, then edges should be a N*2 tensors.

    • If sampled subgraph is heterogeneous, then edges should be a dictionary of edge types and the corresponding edges to exclude.

  • reverse_etypes_mapping (Dict[str, str], optional) – The mapping from the original edge types to their reverse edge types.

Returns:

The node pairs contain both the original edges and their reverse counterparts.

Return type:

Union[Dict[str, torch.Tensor], torch.Tensor]

Examples

>>> edges = {"A:r:B": torch.tensor([[0, 1],[1, 2]]))}
>>> print(gb.add_reverse_edges(edges, {"A:r:B": "B:rr:A"}))
{'A:r:B': torch.tensor([[0, 1],[1, 2]]),
'B:rr:A': torch.tensor([[1, 0],[2, 1]])}

>>> edges = torch.tensor([[0, 1],[1, 2]])
>>> print(gb.add_reverse_edges(edges))
torch.tensor([[1, 0],[2, 1]])