search

williamleif / graphsage-simple

Simple reference implementation of GraphSAGE.
999 stars 242 forks source link

A question about the learning rate. #22

Open johannwyh opened 3 years ago

johannwyh commented 3 years ago

Hello!

I have a question about the learning rate. As is stated in the appendix of GraphSAGE, and are adopted by many other works, the learning rate is usually set to 1e-2, etc. Meanwhile, they usually normalize the input features.

However, in your work, the learning rate is set to 0.7, which is surprisingly high. You do not normalize the input features either. When I try to reset the learning rate to a common one and use the normalized features to train, I find that the model could only converge to a extremely bad performance.

This issue confuses me a lot. Could you help explain a bit?

dongjinkun commented 7 months ago

@johannwyh Hello！ Have you solved this problem？

I am currently facing this issue as well.