Distributed Node Classification node_emb undefined

Questions
#1

Hi,

I am trying to understand the tutorial for Distributed Node Classification and get kinda confused by the section where it takes about mapping the shuffled node/edge IDs to their original IDs.

In the given example code snippet, node_emb is supposed to store the trained code embeddings but from my understanding here, up until this point the graph is not trained yet. I tried to run the given python example file and it gave NameError: name 'node_emb' is not defined. I am wondering how I’m supposed to modify it to get it running. Thank you.

#2

As the doc says: Below let’s assume that the trained node embeddings are stored in the node_emb tensor, which is indexed by the shuffled node IDs., this assume you have obtained node_emb in other ways. It’s just an explanation and usage for the output of dgl.distributed.partition_graph().

As for runnable examples, pls refer to dgl/examples/pytorch/graphsage/dist at master · dmlc/dgl · GitHub, dgl/examples/pytorch/rgcn/experimental at master · dmlc/dgl · GitHub.

#3

Ah my bad… Thank you.

#4

This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.