# PPNP and APPNP
<p align="center">
<img src="https://raw.githubusercontent.com/gasteigerjo/ppnp/master/ppnp_model.svg?sanitize=true" width="600">
</p>
TensorFlow and PyTorch implementations of the model proposed in the paper:
**[Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://www.daml.in.tum.de/ppnp)**
by Johannes Gasteiger, Aleksandar Bojchevski, Stephan Günnemann
Published at ICLR 2019.
Note that the author's name has changed from Johannes Klicpera to Johannes Gasteiger.
## Run the code
The easiest way to get started is by looking at the notebook `simple_example_tensorflow.ipynb` or `simple_example_pytorch.ipynb`. The notebook `reproduce_results.ipynb` shows how to reproduce the results from the paper.
## Requirements
The repository uses these packages:
```
numpy
scipy
tensorflow>=1.6,<2.0
pytorch>=1.5
```
You can install all requirements via `pip install -r requirements.txt`.
However, in practice you will only need either TensorFlow or PyTorch, depending on which implementation you use.
If you use the `networkx_to_sparsegraph` method for importing other datasets you will additionally need NetworkX.
## Installation
To install the package, run `python setup.py install`.
## Datasets
In the `data` folder you can find several datasets. If you want to use other (external) datasets, you can e.g. use the `networkx_to_sparsegraph` method in `ppnp.data.io` for converting NetworkX graphs to our SparseGraph format.
The Cora-ML graph was extracted by Aleksandar Bojchevski, and Stephan Günnemann. *"Deep gaussian embedding of attributed graphs: Unsupervised inductive learning via ranking."* ICLR 2018,
while the raw data was originally published by Andrew Kachites McCallum, Kamal Nigam, Jason Rennie, and Kristie Seymore. *"Automating the construction of internet portals with machine learning."* Information Retrieval, 3(2):127–163, 2000.
The Citeseer graph was originally published by Prithviraj Sen, Galileo Namata, Mustafa Bilgic, Lise Getoor, Brian Gallagher, and Tina Eliassi-Rad.
*"Collective Classification in Network Data."* AI Magazine, 29(3):93–106, 2008.
The PubMed graph was originally published by Galileo Namata, Ben London, Lise Getoor, and Bert Huang. *"Query-driven Active Surveying for Collective Classification"*. International Workshop on Mining and Learning with Graphs (MLG) 2012.
The Microsoft Academic graph was originally published by Oleksandr Shchur, Maximilian Mumme, Aleksandar Bojchevski, Stephan Günnemann. *"Pitfalls of Graph Neural Network Evaluation"*. Relational Representation Learning Workshop (R2L), NeurIPS 2018.
## Contact
Please contact j.gasteiger@in.tum.de in case you have any questions.
## Cite
Please cite our paper if you use the model or this code in your own work:
```
@inproceedings{gasteiger_predict_2019,
title = {Predict then Propagate: Graph Neural Networks meet Personalized PageRank},
author = {Gasteiger, Johannes and Bojchevski, Aleksandar and G{\"u}nnemann, Stephan},
booktitle={International Conference on Learning Representations (ICLR)},
year = {2019}
}
```
没有合适的资源?快使用搜索试试~ 我知道了~
基于GNN图神经网络预测(Python完整源码数据包)
共32个文件
py:19个
ipynb:4个
npz:4个
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
5星 · 超过95%的资源 28 下载量 5 浏览量
2022-11-22
22:50:42
上传
评论 11
收藏 8.34MB ZIP 举报
温馨提示
基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包) 基于GNN图神经网络预测(Python完整源码数据包)
资源推荐
资源详情
资源评论
收起资源包目录
基于GNN图神经网络预测.zip (32个子文件)
ppnp-master
reproduce_results.ipynb 46KB
simple_example_pytorch.ipynb 20KB
reproduce_results_pytorch.ipynb 42KB
simple_example_tensorflow.ipynb 15KB
LICENSE 1KB
ppnp_model.svg 81KB
requirements.txt 46B
setup.py 333B
.gitignore 39B
ppnp
preprocessing.py 3KB
data
io.py 5KB
citeseer.npz 1.29MB
cora_ml.npz 1.55MB
__init__.py 0B
ms_academic.npz 12.24MB
sparsegraph.py 15KB
pubmed.npz 8.52MB
pytorch
ppnp.py 1KB
utils.py 3KB
__init__.py 65B
propagation.py 2KB
earlystopping.py 3KB
training.py 6KB
tensorflow
ppnp.py 3KB
utils.py 1KB
__init__.py 65B
model.py 4KB
propagation.py 2KB
earlystopping.py 3KB
training.py 6KB
__init__.py 0B
README.md 3KB
共 32 条
- 1
前程算法屋
- 粉丝: 4159
- 资源: 711
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
- 1
- 2
- 3
- 4
- 5
- 6
前往页