LG-GNN
LG-GNN copied to clipboard
edge_weight and mi loss
Thank you so much for sharing the work!but I have some doubts about the following points:
Do we not need to take the negative of the mutual information loss?Should we be minimizing the mutual information loss?
Also, in the GlobalGNN module, the calculated edge_weight does not seem to be used.
I look forward to your explanation!
非常感谢你的代码,很棒的工作!但是我对下面的几点有些疑惑,互信息损失不用取负吗,是最小化互信息损失吗,还有在globalgnn模块,所求的edge_weight,好像没有用上?期待你的解答~