Skip to content
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

code on citeseer dataset turn problem #6

Open
xcgydfjjjderg opened this issue Nov 8, 2022 · 0 comments
Open

code on citeseer dataset turn problem #6

xcgydfjjjderg opened this issue Nov 8, 2022 · 0 comments

Comments

@xcgydfjjjderg
Copy link

Dear Professor, the thing is that I downloaded the code of this paper " RWR-GAE: Random Walk Regularization for Graph Auto Encoders" for many experiments, but there is a gap between my experimental results and the data given in the original paper. The specific parameters of my experiment are as follows: python train.py --model="gcn_ae" --dataset-str="citeseer" --dw=1 --epochs=200 --walk-length=30 --window-size=30 - number - walks = 50 - lr_dw = 0.01. python train.py --model="gcn_ae" --dataset-str="citeseer" --dw=1 --epochs=200 --walk-length=5 --window-size=3 - number - walks = 5 - lr_dw = 0.01. I use two different sets of parameters but get the same result, this is why. According to the parameters given in the paper, I have done many experiments on the clustering task of Citeseer dataset, but the results are the same every time. The maximum value of ACC was 0.534 , respectively. There is a difference between ACC of 0.616 given in the paper. So I was worried whether there was a problem with the parameters I gave or some other reason.and I hope you can give me some guidance in your busy schedule, I will be very grateful。Thank you very much.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant