项目文件夹

文件

T

文件历史

Jinjing Zhou 71283997ce Integrate Regression Test with Jenkins (#2448 )

* add bench jenkins

* instance type

* fix

* fix

* fix

* 111

* test

* 111

* 111

* fix

* test

* run

* fix

* fix

* fix

* fix

* fix

* publish results

* 111

* regression

* launch ec2 script

* fix

* add

* run on master

* change

* rrr

* run gpu

* fix

* fix

* try fix

* fix

* ff

* fix

* fix

* fix

* refactor

* fix

* fix

* update

* fix

* fix

* fix

* fix

* remove import torchtext

* add shm size

* update

* fix

* fix

* fix

* fix

* fix this!!!!

* 111

* fix

* remove verbose

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* fix

* update readme

* fix

* fix

* fix

* change asv default to head

* commit sage and rgcn

* fix

* update

2021-01-11 16:01:51 +08:00

gcn_mp.py

[Dataset] Citation graph (#1902 )

2020-08-01 19:25:50 +08:00

gcn.py

[Refactor] Interface of nn modules (#798 )

2019-08-27 22:29:25 +08:00

README.md

[Example] rm gcn spmv (#2044 )

2020-08-18 17:48:38 +08:00

train.py

Integrate Regression Test with Jenkins (#2448 )

2021-01-11 16:01:51 +08:00

README.md

Graph Convolutional Networks (GCN)

Paper link: https://arxiv.org/abs/1609.02907
Author's code repo: https://github.com/tkipf/gcn. Note that the original code is implemented with Tensorflow for the paper.

Dependencies

PyTorch 0.4.1+
requests

bash pip install torch requests

Codes

The folder contains three implementations of GCN:

gcn.py uses DGL's predefined graph convolution module.
gcn_mp.py uses user-defined message and reduce functions. Modify train.py to switch between different implementations.

Results

Run with following (available dataset: "cora", "citeseer", "pubmed")

python3 train.py --dataset cora --gpu 0 --self-loop

cora: ~0.810 (0.79-0.83) (paper: 0.815)
citeseer: 0.707 (paper: 0.703)
pubmed: 0.792 (paper: 0.790)