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

第五章代码有错误 #54

Closed
Ireliafans opened this issue Apr 2, 2021 · 6 comments
Closed

第五章代码有错误 #54

Ireliafans opened this issue Apr 2, 2021 · 6 comments

Comments

@Ireliafans
Copy link

第五章的数据有2708个样本,但是训练集验证集 测试集 数据分布分别是140:500:1000,数据划分存在问题。
正确的数据集划分应该把
“train_index = np.arange(y.shape[0]) 数据集大小有问题
val_index = np.arange(y.shape[0], y.shape[0] + 500)”
修改为
“x_shape=1208
train_index = np.arange(x_shape)
val_index = np.arange(x_shape, x_shape + 500)”
数据集分布变成了1208:500:1000 ,测试集效果能从0.805 提高到0.871

@likuanppd
Copy link

GCN里的划分就是140:500:1000,每个label取20个做训练集,不要想当然啊

@Ireliafans
Copy link
Author

Ireliafans commented Apr 20, 2021 via email

@likuanppd
Copy link

3个citation graph上用这个划分很早就有了,是每个label取20个作为训练集,cora是7类,所以就是140个作为训练集

@r1ght0us
Copy link

r1ght0us commented Nov 5, 2021

3个citation graph上用这个划分很早就有了,是每个label取20个作为训练集,cora是7类,所以就是140个作为训练集

您好我想问下这个分类有什么依据在吗

@likuanppd
Copy link

3个citation graph上用这个划分很早就有了,是每个label取20个作为训练集,cora是7类,所以就是140个作为训练集

您好我想问下这个分类有什么依据在吗

从Kipf的GCN [1]开始,Cora、Citeseer、Pubmed这老三样citation graph就一直用这个划分了,每个类别20个作为训练集

https://arxiv.org/pdf/1609.02907.pdf?fbclid=IwAR0BgJeoKHIAvPuSE9fJ0_IQOEu5l75yxyNo7PUC08RTOFlm_IIo5YmcnQM

[1] Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR).

@r1ght0us
Copy link

r1ght0us commented Nov 5, 2021

3个citation graph上用这个划分很早就有了,是每个label取20个作为训练集,cora是7类,所以就是140个作为训练集

您好我想问下这个分类有什么依据在吗

从Kipf的GCN [1]开始,Cora、Citeseer、Pubmed这老三样citation graph就一直用这个划分了,每个类别20个作为训练集

https://arxiv.org/pdf/1609.02907.pdf?fbclid=IwAR0BgJeoKHIAvPuSE9fJ0_IQOEu5l75yxyNo7PUC08RTOFlm_IIo5YmcnQM

[1] Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR).

太牛逼了,谢谢您!终于找到这是为啥了

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

4 participants