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
this code is not consistent with paper #3
Comments
首先非常感谢您对我们工作的兴趣。代码中这里是分为了两种层融合策略进行的实验,论文中考虑的是self.connect_way=='concat'的情况。 |
|
哦哦,这个地方是参考的ngcf的做法,加入了正则化项,在论文的公式17中写了。
…---Original---
From: "ShiyangZhu"<notifications@github.com>
Date: 2021/3/5 15:57:29
To: "sunshinelium/Bi-TGCF"<Bi-TGCF@noreply.github.com>;
Cc: "sunshinelium"<sunshinelmj@qq.com>;"Comment"<comment@noreply.github.com>;
Subject: Re: [sunshinelium/Bi-TGCF] this code is not consistent with paper (#3)
norm_embeddings_s = tf.math.l2_normalize(ego_embeddings_s, axis=1)
抱歉可能我没表达清楚意思,请问这里为什么要做 L2呢?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
可是这个l2正则项为什么要在后面concat到一起呢?而且这里是多层GCN卷积的部分,正则项也不应该在这里出现呀。 |
这个地方应该不是正则化项,只是通过对特征进行正则化来降低了特征的值,避免特征值大可能带来的梯度问题吧,这里我完全采用的NGCF代码中的处理方式,我的理解是这样,或许你可以问下NGCF的作者?
…---Original---
From: "ShiyangZhu"<notifications@github.com>
Date: 2021/3/5 16:05:19
To: "sunshinelium/Bi-TGCF"<Bi-TGCF@noreply.github.com>;
Cc: "sunshinelium"<sunshinelmj@qq.com>;"Comment"<comment@noreply.github.com>;
Subject: Re: [sunshinelium/Bi-TGCF] this code is not consistent with paper (#3)
可是这个l2正则项为什么要在后面concat到一起呢?而且这里是多层GCN卷积的部分,正则项也不应该在这里出现呀。
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
好的了解到,感谢您的回复。 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
where
why you add norm_embedding to all_embeddings_s?
this code is not consistent with paper !!!
The text was updated successfully, but these errors were encountered: