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

Ask For help #2

Open
ghost opened this issue Jul 7, 2020 · 5 comments
Open

Ask For help #2

ghost opened this issue Jul 7, 2020 · 5 comments

Comments

@ghost
Copy link

ghost commented Jul 7, 2020

Thank you for your contribution.
The form of deepwalk's embedding is as follows,
图片
How do we need to preprocess to satisfy the input of the program? Can you give me some ideas?
Thank you very much.

@UalwaysKnow
Copy link
Owner

UalwaysKnow commented Jul 9, 2020 via email

@ghost
Copy link
Author

ghost commented Jul 23, 2020

you might delete the first line, and then delete the id of each vector, you
will get the final matrix which size is 5313*128

bigfour [email protected] 于2020年7月7日周二 下午8:15写道:

Thank you for your contribution.
The form of deepwalk's embedding is as follows,
[image: 图片]
https://user-images.githubusercontent.com/28142229/86779698-6de78580-c08e-11ea-922c-326b30c9961c.png
How do we need to preprocess to satisfy the input of the program? Can you
give me some ideas?
Thank you very much.


You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#2>, or
unsubscribe
https://github.com/notifications/unsubscribe-auth/AMUFY6GZXPKWUIMPMF2RVGLR2MGW7ANCNFSM4OSYFI4A
.
您好,在复现您的代码时,对一个输入文件不是特别清楚,代码如下:
#gailv:三行---序号,度数,概率
parser.add_argument('--input_netl_weight', nargs='?', default='../example_embeddings/four-weight.txt', help='Input left sampling weight')
parser.add_argument('--input_netr_weight', nargs='?', default='../example_embeddings/twit-weight.txt', help='Input right sampling weight')
我理解的是:每行表示一个节点的信息,包含三个元素,分别是“节点编号、节点的度、概率”,但是我对这个概率不是很清楚。
这个”four-weight.txt“的格式是什么样的?这个概率是如何计算得到的?
十分感谢!!!
我的邮箱是[email protected],希望有机会能和您有更多的交流。谢谢

@UalwaysKnow
Copy link
Owner

UalwaysKnow commented Jul 23, 2020 via email

@bearlzy
Copy link

bearlzy commented Aug 9, 2020

您好,在复现您的代码时遇到了一些问题,我想请问您关于输入文件的具体内容以及格式,参数如下:
--input_netl_nodes --input_netr_nodes --input_netl_weight --input_netr_weight --input_netl_anchors --input_netr_anchors --input_train_anchors --input_test_anchors --input_test_netl_embeddings --input_test_netr_embeddings --left_nodes_num --right_nodes_num --train_anchors_num --test_anchors_num,如果能得到您的回复我将十分感谢,我的邮箱是[email protected]

@bearlzy
Copy link

bearlzy commented Aug 10, 2020

您好,我复现代码得出的结果都很小,不知道是不是我输入的数据存在问题,结果如下:
image
想请问一下您的准确率具体是怎么计算的,具体代码如下:
image
image
期待您的回复,十分感谢,我的邮箱是[email protected]

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