Add GBP(Graph Neural Networks via Bidirectional Propagation)

[userTogrul]

Scalable Graph Neural Networks via Bidirectional Propagation.
Thinks to improve the performance:

• changing C++ code to Python
• precomputing the features of dataset
• implement in the node classification task the process of precomputing

Paper link: https://github.com/chennnM/GBP

[THINK2TRY]

Hi @userTogrul.
Thanks for your contribution. GBP is an interesting model and it would be exciting if you could reimplement it in Python. But it seems that the "precomputing the features" is not included in current code. Could you add the remaining part of GBP and reproduce the result? Many thanks.

[userTogrul]

I actually worked on that. The precomputing part is that part implemented in CPP. They converted it using CMAKE and SWIG, so I was not able to utilize them well.

[userTogrul]

But I want to do the precomputing. I just have timing problems.

[GooLiang]

I actually worked on that. The precomputing part is that part implemented in CPP. They converted it using CMAKE and SWIG, so I was not able to utilize them well.

hello, is there any new progress on this issue?