I have a dgl graph g
as follows
u, v = torch.tensor([0, 0, 0, 1]), torch.tensor([1, 2, 3, 3])
g = dgl.graph((u, v))
How can I obtain the neighbors of node 3
directly from the graph object?
I have a dgl graph g
as follows
u, v = torch.tensor([0, 0, 0, 1]), torch.tensor([1, 2, 3, 3])
g = dgl.graph((u, v))
How can I obtain the neighbors of node 3
directly from the graph object?
Hi! I’ve dealt with something similar and I’ve done two things:
1- Convert DGL graph to networks: dgl.to_networkx — DGL 0.6.1 documentation
2- Use networks neighbours function: Graph.neighbors — NetworkX 2.7.1 documentation
Thanks for the reply!
I could use different workarounds to identify the neighbors of a node like you have suggested ( also one can use an adjacency list). However, I was hoping that the DGLGraph object would have such a capability, given that, we can add or remove edges for a dgl graph.
Besides what @neo said, in_edges
and out_edges
also work (and it could give you the neighboring edges as well).
This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.