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.

Sign up for GitHub

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

Jump to bottom

There is a big difference between the experimental data and the actual operation results #3

Open
lilinbaba opened this issue Sep 4, 2020 · 11 comments
Open

There is a big difference between the experimental data and the actual operation results #3

lilinbaba opened this issue Sep 4, 2020 · 11 comments

Comments

@lilinbaba
Copy link

I read your paper and I'm interested in it. But I have doubts about the detailed implementation process of the algorithm.I run your open source code and find that the actual results are quite different from the data in the paper. Can you provide all the parameters needed to run the code?
@CHERYZ
Copy link

CHERYZ commented Sep 28, 2022

+1

@xcgydfjjjderg
Copy link

I also encountered the same problem. There is a gap between the experimental results and the original paper when I downloaded the open source code according to the instructions in the README file. Could you please give all the parameters, thank you very much.

@xcgydfjjjderg
Copy link

I read your paper and I'm interested in it. But I have doubts about the detailed implementation process of the algorithm.I run your open source code and find that the actual results are quite different from the data in the paper. Can you provide all the parameters needed to run the code?

Did you solve it, I have the same problem. And I emailed the author with no response. I plan to use this as the opening topic of the thesis, but there is a gap in the experimental data, so please let me know if you have solved it. Thank you very much.

@xcgydfjjjderg
Copy link

+1

Did you solve it, I have the same problem. And I emailed the author with no response. I plan to use this as the opening topic of the thesis, but there is a gap in the experimental data, so please let me know if you have solved it. Thank you very much.

@lilinbaba
Copy link
Author

lilinbaba commented Oct 30, 2022 via email

@lilinbaba
Copy link
Author

lilinbaba commented Oct 30, 2022 via email

@xcgydfjjjderg
Copy link

我也觉得我还打算用它开题，开题报告都写好了下周就开了但是我实验跑出来有差距，我尝试过调参但是也没效果。我给作者发邮件两个是假的，只有一个账号能发但是一直没收到回复。然后尝试按照代码输入参数，但是当我输入--context=1代码就报错。怎么办要死了。Traceback (most recent call last):
File "train.py", line 201, in
gae_for(args)
File "train.py", line 120, in gae_for
curr_pair = (int(walk[center_node_pos]), [])
NameError: name 'center_node_pos' is not defined
File "train.py", line 119, in gae_for
curr_pair = (int(walk[center_node_pos]), [])
UnboundLocalError: local variable 'center_node_pos' referenced before assignment

@lilinbaba
Copy link
Author

lilinbaba commented Oct 30, 2022 via email

@xcgydfjjjderg
Copy link

能跑，就是结果不对，想跑的话可以调代码，不要再考虑改进了   李琳 @.***  
…
------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年10月30日(星期天) 下午5:16 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [MysteryVaibhav/RWR-GAE] There is a big difference between the experimental data and the actual operation results (#3) 我也觉得我还打算用它开题，开题报告都写好了下周就开了但是我实验跑出来有差距，我尝试过调参但是也没效果。我给作者发邮件两个是假的，只有一个账号能发但是一直没收到回复。然后尝试按照代码输入参数，但是当我输入--context=1代码就报错。怎么办要死了。Traceback (most recent call last): File "train.py", line 201, in gae_for(args) File "train.py", line 120, in gae_for curr_pair = (int(walk[center_node_pos]), []) NameError: name 'center_node_pos' is not defined File "train.py", line 119, in gae_for curr_pair = (int(walk[center_node_pos]), []) UnboundLocalError: local variable 'center_node_pos' referenced before assignment — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

哥/姐你也是研究这块的吗？开题要创新点，我都担心我后续实验能不能跑出论文的效果可能效果差就完蛋了。我最近把另一篇论文的一个创新点引入但是效果很差在这个模型上跑，感觉要崩了。

@xcgydfjjjderg
Copy link

xcgydfjjjderg commented Nov 2, 2022 via email

@xcgydfjjjderg
Copy link

能跑，就是结果不对，想跑的话可以调代码，不要再考虑改进了   李琳 @.***  
…
------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2022年10月30日(星期天) 下午5:16 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [MysteryVaibhav/RWR-GAE] There is a big difference between the experimental data and the actual operation results (#3) 我也觉得我还打算用它开题，开题报告都写好了下周就开了但是我实验跑出来有差距，我尝试过调参但是也没效果。我给作者发邮件两个是假的，只有一个账号能发但是一直没收到回复。然后尝试按照代码输入参数，但是当我输入--context=1代码就报错。怎么办要死了。Traceback (most recent call last): File "train.py", line 201, in gae_for(args) File "train.py", line 120, in gae_for curr_pair = (int(walk[center_node_pos]), []) NameError: name 'center_node_pos' is not defined File "train.py", line 119, in gae_for curr_pair = (int(walk[center_node_pos]), []) UnboundLocalError: local variable 'center_node_pos' referenced before assignment — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

学姐很冒昧再次打扰您，真的非常对不起。我能最后在请教您一个问题吗，就是我在跑citeseer数据集的时候和原论文差距非常大我不知道为什么感觉很崩溃，是citeseer数据集部分的代码不对吗？在cora数据集还没啥问题但是在citeseer数据集上测试，问题非常大。只能厚着脸皮再来请教您，您当初遇见过这个问题吗？是不是有地方代码写的不对，您之前说想跑的话可以调代码，这地方是指调参还是我需要重写部分代码，还请您指教万分感谢，跪谢您。再次感谢您，好人一生平安！

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@CHERYZ @lilinbaba @xcgydfjjjderg