-
Notifications
You must be signed in to change notification settings - Fork 11
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Questions on getting the results shown in the table #1
Comments
My original code works perfectly or even has better performance with using PN, this code is simplified version and I'm working on finding the bugs. Will get back to you soon. |
Hi Yongcheng, I found that the way of normalizing adjacency matrix affects the performance of GCN a lot with PairNorm. Please try the updated code. What's more, please start from using PN instead of PN-SI, I found a small bug in my old problem of PN which makes the performance bad for GCN. Now it should works good. |
Without specifying random seed, you may need test several times to reduce the variance. Please have a test and I will close the thread now. |
|
Hi Lingxiao, Thanks for the quick response! I really appreciate it. I will try your updated code today. Best, |
Hi Lingxiao,
Thank you for the great code. I am new to this area. So I would like to apologize first, considering that my questions might be trivial.
I wonder how to get the results shown in Table 2 of the paper. For example, for GCN-PN with 10 layers and 100% missing rate on Cora, I run the following command:
python main.py --data cora --model DeepGCN --nlayer 10 --missing_rate 100 --norm_mode PN-SI --residual 0
Instead of getting the acc of 0.731 shown in the paper, I obtained the following results:
Test set results: loss 1.084, acc 0.637.
I also found the same issue for other items in the table.
There might be something wrong in my experimental settings, and I would greatly appreciate it if you could help me. Thank you in advance.
Best,
Yongcheng
The text was updated successfully, but these errors were encountered: