How can I use graphRNN code to generate graphs with costume node labels or with node attributes?

[thesaturdayafternoon]

Hello, How can I use graphRNN code to generate graphs with costume node labels or with node attributes? Here is my problem: by modifying 'create_graphs.py', I created a training set of grid2D graphs where instead of default labels such as (0,0), (0,1), (1,0),...the nodes have costume labels such as a,b,c,... and they have also a node attribute. However when I train graphRNN with these graphs, then the graphs generated by graphRNN have default labels (0,0), (0,1), (1,0),...and they have no node attributes. Do you have any solution for this problem? Thanks

[Nuyoah003]

I also encountered the same problem. I think the reason should be that only the adjacency matrix is considered in the dataset processing, so the node attributes are automatically ignored. How can the author solve this problem? thank you

[geopapa11]

I think I have created a solution for this. If many people are interested to have GraphRNN support node labels I can upload an extension version of GraphRNN in my github.