kuhanw

Hey all, As a sanity check, I just tried to reproduce the twitter results from http://suriyadeepan.github.io/2016-12-31-practical-seq2seq/, and my training loss does not seem to decrease significantly just using the out...

Is there a fix for this aside from downgrading tensorflow? I am having the same issue.

Hi, I am interested in this as well. My thought was similar to @Jhy1993. Concatenate the features of the node types together, maybe you can include a one hot encoding...

Hi, I would also be interested in this. I think I am having a similar issue trying to apply graphsage to a large graph with large feature matrices that is...