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

关于baseline复现问题 #243

Closed
ll0ruc opened this issue Sep 13, 2022 · 2 comments
Closed

关于baseline复现问题 #243

ll0ruc opened this issue Sep 13, 2022 · 2 comments

Comments

@ll0ruc
Copy link

ll0ruc commented Sep 13, 2022

您好,注意到21-WWW-MHCN论文中对比的模型包含rating任务的GraphRec和ranking任务的DiffNet++。
请问,你当时的GraphRec是怎么适应调整到ranking任务的?我尝试了下,Graphrec加bpr loss,用在ranking任务上,分类准确率很低。
同时有注意到Diffnet原作者放出的Diffnet-code和Diffnet论文不一致,请问你当时是使用基于论文公式复现的网络吗。
在自己模型跟这些baseline相比时,如何保证对比的一致性

@Coder-Yu
Copy link
Owner

Coder-Yu commented Sep 13, 2022

GraphRec 网上有好几个第三方实现的版本,我是选择了其中的一个版本。该模型原始代码质量确实比较差,看网上反响论文结果存疑,建议别follow了。Diffnet要求free embedding和content embedding作为输入,但大部分论文采用的数据集没有content,就只使用了free embedding。
复现时,同样experimental setting下复现不出来对方结果按自己跑的就行,能大致复现的使用对方结果。我是这么做的。

@Coder-Yu
Copy link
Owner

diffnet我是用自己实现的代码跑的 效果较差。同样结论在recbole-gnn里面也有,建议参考。

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

2 participants