dmlc--dgl
Minjie Wang
565f0c88fc
* refactor graph conv * docs & tests * fix lint * fix lint * fix lint * fix lint script * fix lint * Update * Style fix * Fix style * Fix style * Fix gpu case * Fix for gpu case * Hotfix edgesoftmax docs * Handle repeated features * Add docstring * Set default arguments * Remove dropout from nn.conv * Fix * add util fn for renaming * revert gcn_spmv.py * mx folder * fix wierd bug * fix mx * fix lint
994 B
994 B
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.pyuses DGL's predefined graph convolution module.gcn_mp.pyuses user-defined message and reduce functions.gcn_spmv.pyimproves fromgcn_mp.pyby using DGL's builtin functions so SPMV optimization could be applied. Modifytrain.pyto switch between different implementations.
Results
Run with following (available dataset: "cora", "citeseer", "pubmed")
python train.py --dataset cora --gpu 0
- cora: ~0.810 (0.79-0.83) (paper: 0.815)
- citeseer: 0.707 (paper: 0.703)
- pubmed: 0.792 (paper: 0.790)