[Doc] Fix DGMG part in README (#270)

* Fix DGMG epoch time

* Fix README for DGMG

* update

examples/pytorch/README.md

@@ -12,10 +12,10 @@ Here is a summary of the model accuracy and training speed. Our testbed is Amazo
 
 | Model | Reported <br> Accuracy | DGL <br> Accuracy | Author's training speed (epoch time) | DGL speed (epoch time) | Improvement |
 | ----- | ----------------- | ------------ | ------------------------------------ | ---------------------- | ----------- |
-| GCN   | 81.5% | 81.0% | 0.0051s (TF) | 0.0042s | 1.17x |
-| TreeLSTM | 51.0% | 51.72% | 14.02s (DyNet) | 3.18s | 4.3x |
-| R-GCN <br> (classification) | 73.23% | 73.53% | 0.2853s (Theano) | 0.0273s | 10.4x |
-| R-GCN <br> (link prediction) | 0.158 | 0.151 | 2.204s (TF) | 0.633s | 3.5x |
-| JTNN | 96.44% | 96.44% | 1826s (Pytorch) | 743s | 2.5x |
-| LGNN | 94% | 94% | n/a | 1.45s | n/a |
-| DGMG | 84% | 90% | n/a | 1 hr | n/a |
+| [GCN](https://arxiv.org/abs/1609.02907)   | 81.5% | 81.0% | [0.0051s (TF)](https://github.com/tkipf/gcn) | 0.0042s | 1.17x |
+| [TreeLSTM](http://arxiv.org/abs/1503.00075) | 51.0% | 51.72% | [14.02s (DyNet)](https://github.com/clab/dynet/tree/master/examples/treelstm) | 3.18s | 4.3x |
+| [R-GCN <br> (classification)](https://arxiv.org/abs/1703.06103) | 73.23% | 73.53% | [0.2853s (Theano)](https://github.com/tkipf/relational-gcn) | 0.0273s | 10.4x |
+| [R-GCN <br> (link prediction)](https://arxiv.org/abs/1703.06103) | 0.158 | 0.151 | [2.204s (TF)](https://github.com/MichSchli/RelationPrediction) | 0.633s | 3.5x |
+| [JTNN](https://arxiv.org/abs/1802.04364) | 96.44% | 96.44% | [1826s (Pytorch)](https://github.com/wengong-jin/icml18-jtnn) | 743s | 2.5x |
+| [LGNN](https://arxiv.org/abs/1705.08415) | 94% | 94% | n/a | 1.45s | n/a |
+| [DGMG](https://arxiv.org/pdf/1803.03324.pdf) | 84% | 90% | n/a | 238s | n/a |

examples/pytorch/dgmg/README.md

@@ -13,6 +13,15 @@ Yujia Li, Oriol Vinyals, Chris Dyer, Razvan Pascanu, Peter Battaglia.
 - Train with batch size 1: `python main.py`
 - Train with batch size larger than 1: `python 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.