dmlc--dgl
Mufei LiLearning Deep Generative Models of Graphs
This is an implementation of Learning Deep Generative Models of Graphs by Yujia Li, Oriol Vinyals, Chris Dyer, Razvan Pascanu, Peter Battaglia.
For molecule generation, see our model zoo for Chemistry.
Dependencies
- Python 3.5.2
- Pytorch 0.4.1
- Matplotlib 2.2.2
Usage
- Train with batch size 1:
python3 main.py - Train with batch size larger than 1:
python3 main_batch.py.
Performance
90% accuracy for cycles compared with 84% accuracy reported in the original paper.
Speed
On AWS p3.2x instance (w/ V100), one epoch takes ~526s for batch size 1 and takes ~238s for batch size 10.
Acknowledgement
We would like to thank Yujia Li for providing details on the implementation.