提交 af936913 编写于 作者: W wangwenjin

add experiment result

上级 2bd2b054
......@@ -27,3 +27,9 @@ python train.py --lr 1e-2 --rc 0 --batch_size 1024 --epochs 100
- hidden_size_v: the size of value vectors
- hidden_size_m: the size of projection space for computing gates
- hidden_size_o: the size of output of GaAN layer
## Performance
We train our models for 100 epochs and report the **rocauc** on the test dataset.
|dataset|mean|std|
|-|-|-|
|ogbn-proteins|0.7786|0.0048|
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册