Graph Convolution Network for PyTorch
Pytorch 1.0 with python 3.7.
GCN implementation for paper: Semi-Supervised Classification with Graph Convolutional Networks
| dataset | Citeseea | Cora | Pubmed | NELL |
|---|---|---|---|---|
| GCN(official) | 70.3 | 81.5 | 79.0 | 66.0 |
| This repo. | 81.7 | 78.7 |
Hints:
To achieve 81.7% on Cora dataset, pytorch need 400 epochs.
and it train relatively slower on Pubmed dataset.
python train.py
Hey,
Thanks for your codes!
It seems that you should use the singular form in third personal for some verbs. Such as 'it trains relatively slower'
我想问一下这个GCN相当于低通滤波器，可以用来提取高频特征，如果可以提取，那应该是那一段代码了
how to run this code in citeseer datasets?
I have try ：
features = preprocess_features(features) # [49216, 2], [49216], [2708, 1433]
supports = preprocess_adj(adj)
device = torch.device('cuda')
train_label = torch.from_numpy(y_train).long().to(device)
num_classes = train_label.shape[1]
train_label = train_label.argmax(dim=1)
train_mask = torch.from_numpy(train_mask.astype(np.bool)).bool().to(device)
val_label = torch.from_numpy(y_val).long().to(device)
val_label = val_label.argmax(dim=1)
val_mask = torch.from_numpy(val_mask.astype(np.bool)).bool().to(device)
test_label = torch.from_numpy(y_test).long().to(device)
test_label = test_label.argmax(dim=1)
test_mask = torch.from_numpy(test_mask.astype(np.bool)).bool().to(device)the function masked_loss() may have not softmax.
Hi
Looks like I could not fully reproduce the results.
Can someone help troubleshooting?Thanks.
Lines 41 to 54 in 623aa67
It seems the L2 loss is only execute once on the first layer.
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.