GRAD

毕业：文本图上的图形意识蒸馏

这是用于复制Grad的关键结果的代码：文本图上的图形感知蒸馏。

开始

请前往GradBERT或GradMLP以获取更多说明。

运行代码的依赖项在requirements.txt文件中。

要求和安装

我们还遵循[巨人]的安装过程。

首先让我们设置一个环境

conda create -n " grad " python=3.8
conda activate grad

接下来，我们安装pytorch：

conda install pytorch==1.9.0 cudatoolkit=10.2 -c pytorch
# check the pytorch version and cuda availability
python -c " import torch; print('torch={}, cuda={}'.format(torch.__version__, torch.cuda.is_available())) "

Finall，我们安装了GNN相关软件包

ptcu_version= " 1.9.0+cu102 "
pip install torch-scatter -f " https://pytorch-geometric.com/whl/torch- ${ptcu_version} .html "
pip install torch-sparse -f " https://pytorch-geometric.com/whl/torch- ${ptcu_version} .html "
pip install torch-cluster -f " https://pytorch-geometric.com/whl/torch- ${ptcu_version} .html "
pip install torch-spline-conv -f " https://pytorch-geometric.com/whl/torch- ${ptcu_version} .html "
pip install torch-geometric
pip install ogb==1.3.2
# our ogb version is 1.3.2
python -c " import ogb; from ogb.graphproppred import PygGraphPropPredDataset; print(ogb.__version__) " 

Gradbert嵌入

请从此链接下载预训练的Gradbert节点嵌入https://drive.google.com/drive/folders/1tol67yewyewyogusf4t2qwrds-hbhbg-icx?usp = sharing并在此文件夹中提取它们。请确保提取的文件夹具有此基结构GradBERT/embeddings/ogbn-*/ 。

然后，您可以使用ogbn-arxiv或ogbn-products文件夹，并运行相应的sh命令，以重现OGB排行榜的Gradbert结果。

目录布局

在下面，您可以找到脚本来复制关键结果。

./GRAD
| ---- GradBERT/                     # OGB datasets
|        | ---- embeddings/
|        | ---- ogbn-arxiv/ 
|        |        | ---- gradbert_mlp.sh         # MLP with GradBERT feats
|        |        | ---- gradbert_sage.sh        # SAGE with GradBERT feats
|        |        | ---- RevGAT-ori
|                           | ---- gradbert_RevGAT_ogbnarxiv.sh      # RevGAT with GradBERT feats
|        | ---- ogbn-products/
|        |        | ---- gradbert_mlp.sh         # MLP with GradBERT feats
|        |        | ---- gradbert_giant_sage.sh  # SAGE with GradBERT+GIANT feats
|        |        | ---- SAGN_with_SLE
|                           | ---- Runexp_SAGN_SLE_ogbnproducts_morestages.sh     # SAGN_SLE with GradBERT+GIANT feats                    

| ---- GradMLP/                # CPF data from GLNN
|        | ---- experiments/          	
|        |        | ---- cora_gradmlp.sh
|        |        | ---- cora_gradmlp_kd.sh
|        |        | ---- etc.


Please go to ` GradBERT ` or ` GradMLP ` for more details.