build symmetric adjacency matrix about pygcn HOT 4 CLOSED

Yes, for binary adjacency matrices you are right. In all other cases you need the last term to ensure that only a single edge is kept (the one with largest weight).

from pygcn.

@fansariadeh. Based on my understanding, the original GCN paper considers undirected graphs. In some datasets, the graph may not be undirected ( e.g. store as the directed graph). This line of code can make sure the input graph be undirected.

from pygcn.

I do not understand why adj matrix should be turned into a symmetric matrix. Could you please clarify it?

from pygcn.

@fansariadeh. Based on my understanding, the original GCN paper considers undirected graphs. In some datasets, the graph may not be undirected ( e.g. store as the directed graph). This line of code can make sure the input graph be undirected.

Dear @baojianzhou
That makes sense to me now. I appreciate it.
Cheers,

from pygcn.