矩池云上复现论文 Neural Graph Collaborative Filtering 环境复现

最新推荐文章于 2022-04-06 13:00:41 发布

机器学习是魔鬼

最新推荐文章于 2022-04-06 13:00:41 发布

阅读量361

点赞数 1

分类专栏：笔记文章标签：人工智能论文 anaconda python

本文链接：https://blog.csdn.net/weixin_48344945/article/details/119321075

版权

笔记专栏收录该内容

101 篇文章 3 订阅

订阅专栏

矩池云上复现论文 Neural Graph Collaborative Filtering 环境复现

Neural Graph Collaborative Filtering (NGCF) is a new recommendation framework based on graph neural network, explicitly encoding the collaborative signal in the form of high-order connectivities in user-item bipartite graph by performing embedding propagation.

https://github.com/xiangwang1223/neural_graph_collaborative_filtering

bash /public/script/switch_conda_source.sh

在这里插入图片描述

git clone https://github.com/xiangwang1223/neural_graph_collaborative_filtering.git
bash /public/script/switch_conda_source.sh
conda create -n py36 python=3.6.5

在这里插入图片描述

# To activate this environment, use
#
#     $ conda activate py36
#
# To deactivate an active environment, use
#
#     $ conda deactivate

conda activate py36

在这里插入图片描述

pip install tensorflow-gpu==1.8.0
pip install scipy==1.1.0
pip install scikit-learn==0.19.1
pip install numpy==1.14.3

在这里插入图片描述

cd /neural_graph_collaborative_filtering/NGCF/
python NGCF.py

在这里插入图片描述

Gowalla dataset

python NGCF.py --dataset gowalla --regs [1e-5] --embed_size 64 --layer_size [64,64,64] --lr 0.0001 --save_flag 1 --pretrain 0 --batch_size 1024 --epoch 400 --verbose 1 --node_dropout [0.1] --mess_dropout [0.1,0.1,0.1]

Amazon-book dataset

python NGCF.py --dataset amazon-book --regs [1e-5] --embed_size 64 --layer_size [64,64,64] --lr 0.0005 --save_flag 1 --pretrain 0 --batch_size 1024 --epoch 200 --verbose 50 --node_dropout [0.1] --mess_dropout [0.1,0.1,0.1]