Closed kexinhuang12345 closed 3 years ago
Hi,
In the code, I explicitly save the attention value for each forward pass https://github.com/acbull/pyHGT/blob/63aec910d563da4538f5e84ee2802627350541fe/pyHGT/conv.py#L108
, which you can plot for a given input.
For the tree, I just manually select top-K children with the highest normalized attention score for visualization. If you have further questions just ask me and I can see what I can help.
Hi, thanks for the prompt reply. I am using the DGL version, is it true it corresponds to this variable?
https://github.com/acbull/HGT-DGL/blob/182cc56a133454770a8c1043047cb44555f79853/model.py#L57
yes, that is the attention value.
Hi,
Thanks for the great work. I am wondering if you can provide more details about the meta relation tree (fig 5) generation? If possible, can you provide scripts to generate this tree? Thanks!