code on citeseer dataset turn problem

[xcgydfjjjderg]

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.