gae_in_pytorch-master
所属分类：其他
开发工具：Python
文件大小：569KB
下载次数：1
上传日期：2020-07-06 17:40:54
上 传 者：
曼珠沙华lxf
说明： 图形自动编码器GAE的pytorch实现，可参考论文VGAE
(Implementation of graph self encoder gae with Python)
文件列表:
citeseer_results.png (72667, 2019-12-12)
cora_results.png (73544, 2019-12-12)
data (0, 2019-12-12)
data\ind.citeseer.allx (595021, 2019-12-12)
data\ind.citeseer.graph (61987, 2019-12-12)
data\ind.citeseer.test.index (5000, 2019-12-12)
data\ind.citeseer.tx (260321, 2019-12-12)
data\ind.citeseer.x (31087, 2019-12-12)
data\ind.cora.allx (257305, 2019-12-12)
data\ind.cora.graph (59847, 2019-12-12)
data\ind.cora.test.index (5000, 2019-12-12)
data\ind.cora.tx (148025, 2019-12-12)
data\ind.cora.x (22119, 2019-12-12)
dist.py (852, 2019-12-12)
layers.py (2209, 2019-12-12)
models.py (3550, 2019-12-12)
preprocessing.py (4347, 2019-12-12)
requirements.txt (128, 2019-12-12)
results.png (78016, 2019-12-12)
train.py (3595, 2019-12-12)
utils.py (4428, 2019-12-12)
# Gae In Pytorch
Graph Auto-Encoder in PyTorch
This is a PyTorch/Pyro implementation of the Variational Graph Auto-Encoder model described in the paper:
T. N. Kipf, M. Welling, [Variational Graph Auto-Encoders](https://arxiv.org/abs/1611.07308), NIPS Workshop on Bayesian Deep Learning (2016)
This repository uses some of the code found here: https://github.com/tkipf/pygcn and https://github.com/tkipf/gae.
Tested December 19th, 2018 with PyTorch 1.0 and Pyro 0.3.0.
### Requirements
- Python 2.7
- Pyro 0.3.0
- PyTorch 1.0
- networkx
- scikit-learn
- scipy
- numpy
- matplotlib
- pickle
### To run
After installing all requirements:
```bash
python train.py
```
### Notes
- This implementation uses Pyro's blackbox SVI function with the default ELBO loss. This is slower than the TensorFlow implementation which uses a custom loss function with an analytic solution to the KL divergence term.
- Currently the code is not set up to use a GPU, but the code should be easy to extend to improve running speed
近期下载者：
相关文件：
收藏者：