# GraphEmbedding
[](https://github.com/shenweichen/graphembedding/issues)
[](https://codecov.io/gh/shenweichen/graphembedding)
[](https://www.codacy.com/gh/shenweichen/GraphEmbedding/dashboard?utm_source=github.com&utm_medium=referral&utm_content=shenweichen/GraphEmbedding&utm_campaign=Badge_Grade)
[](./README.md#disscussiongroup--related-projects)
[comment]: <> ([](https://github.com/shenweichen/graphembedding/blob/master/LICENSE))
# Method
| Model | Paper | Note |
| :-------: | :------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------ |
| DeepWalk | [KDD 2014][DeepWalk: Online Learning of Social Representations](http://www.perozzi.net/publications/14_kdd_deepwalk.pdf) | [【Graph Embedding】DeepWalk：算法原理，实现和应用](https://zhuanlan.zhihu.com/p/56380812) |
| LINE | [WWW 2015][LINE: Large-scale Information Network Embedding](https://arxiv.org/pdf/1503.03578.pdf) | [【Graph Embedding】LINE：算法原理，实现和应用](https://zhuanlan.zhihu.com/p/56478167) |
| Node2Vec | [KDD 2016][node2vec: Scalable Feature Learning for Networks](https://www.kdd.org/kdd2016/papers/files/rfp0218-groverA.pdf) | [【Graph Embedding】Node2Vec：算法原理，实现和应用](https://zhuanlan.zhihu.com/p/56542707) |
| SDNE | [KDD 2016][Structural Deep Network Embedding](https://www.kdd.org/kdd2016/papers/files/rfp0191-wangAemb.pdf) | [【Graph Embedding】SDNE：算法原理，实现和应用](https://zhuanlan.zhihu.com/p/56637181) |
| Struc2Vec | [KDD 2017][struc2vec: Learning Node Representations from Structural Identity](https://arxiv.org/pdf/1704.03165.pdf) | [【Graph Embedding】Struc2Vec：算法原理，实现和应用](https://zhuanlan.zhihu.com/p/56733145) |
# How to run examples
1. clone the repo and make sure you have installed `tensorflow` or `tensorflow-gpu` on your local machine.
2. run following commands
```bash
python setup.py install
cd examples
python deepwalk_wiki.py
```
## DisscussionGroup & Related Projects
<html>
<table style="margin-left: 20px; margin-right: auto;">
<tr>
<td>
公众号：<b>浅梦学习笔记</b><br><br>
<a href="https://github.com/shenweichen/GraphEmbedding">
<img align="center" src="./pics/code.png" />
</a>
</td>
<td>
微信：<b>deepctrbot</b><br><br>
<a href="https://github.com/shenweichen/GraphEmbedding">
<img align="center" src="./pics/deepctrbot.png" />
</a>
</td>
<td>
<ul>
<li><a href="https://github.com/shenweichen/AlgoNotes">AlgoNotes</a></li>
<li><a href="https://github.com/shenweichen/DeepCTR">DeepCTR</a></li>
<li><a href="https://github.com/shenweichen/DeepMatch">DeepMatch</a></li>
<li><a href="https://github.com/shenweichen/DeepCTR-Torch">DeepCTR-Torch</a></li>
</ul>
</td>
</tr>
</table>
</html>
# Usage
The design and implementation follows simple principles(**graph in,embedding out**) as much as possible.
## Input format
we use `networkx`to create graphs.The input of networkx graph is as follows:
`node1 node2 <edge_weight>`
## DeepWalk
```python
G = nx.read_edgelist('../data/wiki/Wiki_edgelist.txt',create_using=nx.DiGraph(),nodetype=None,data=[('weight',int)])# Read graph
model = DeepWalk(G,walk_length=10,num_walks=80,workers=1)#init model
model.train(window_size=5,iter=3)# train model
embeddings = model.get_embeddings()# get embedding vectors
```
## LINE
```python
G = nx.read_edgelist('../data/wiki/Wiki_edgelist.txt',create_using=nx.DiGraph(),nodetype=None,data=[('weight',int)])#read graph
model = LINE(G,embedding_size=128,order='second') #init model,order can be ['first','second','all']
model.train(batch_size=1024,epochs=50,verbose=2)# train model
embeddings = model.get_embeddings()# get embedding vectors
```
## Node2Vec
```python
G=nx.read_edgelist('../data/wiki/Wiki_edgelist.txt',
create_using = nx.DiGraph(), nodetype = None, data = [('weight', int)])#read graph
model = Node2Vec(G, walk_length = 10, num_walks = 80,p = 0.25, q = 4, workers = 1)#init model
model.train(window_size = 5, iter = 3)# train model
embeddings = model.get_embeddings()# get embedding vectors
```
## SDNE
```python
G = nx.read_edgelist('../data/wiki/Wiki_edgelist.txt',create_using=nx.DiGraph(),nodetype=None,data=[('weight',int)])#read graph
model = SDNE(G,hidden_size=[256,128]) #init model
model.train(batch_size=3000,epochs=40,verbose=2)# train model
embeddings = model.get_embeddings()# get embedding vectors
```
## Struc2Vec
```python
G = nx.read_edgelist('../data/flight/brazil-airports.edgelist',create_using=nx.DiGraph(),nodetype=None,data=[('weight',int)])#read graph
model = Struc2Vec(G, 10, 80, workers=4, verbose=40, ) #init model
model.train(window_size = 5, iter = 3)# train model
embeddings = model.get_embeddings()# get embedding vectors
```
GraphEmbedding-master(2023.1.19上传).zip
需积分: 5 35 浏览量
2023-01-19
15:03:36
上传
评论
收藏 310KB ZIP 举报
GraphEmbedding-master.zip （44个子文件） 
GraphEmbedding-master GraphEmbedding-master ge 
utils.py 1KB __init__.py 21B walker.py 10KB models __init__.py 207B deepwalk.py 2KB struc2vec.py 14KB sdne.py 6KB node2vec.py 2KB line.py 7KB classify.py 3KB alias.py 1KB setup.py 818B .github workflows ci.yml 2KB .gitattributes 66B data flight usa-airports.edgelist 159KB
labels-europe-airports.txt 2KB labels-usa-airports.txt 9KB labels-brazil-airports.txt 687B brazil-airports.edgelist 6KB europe-airports.edgelist 39KB wiki wiki_labels.txt 16KB Wiki_edgelist.txt 158KB Wiki_category.txt 16KB LICENSE 1KB tests __init__.py 0B deepwalk_test.py 396B sdne_test.py 459B Wiki_edgelist.txt 19B line_test.py 391B struct2vec_test.py 370B node2vec_test.py 596B examples deepwalk_wiki.py 1KB node2vec_wiki.py 2KB struc2vec_flight.py 2KB node2vec_flight.py 2KB line_wiki.py 1KB sdne_wiki.py 1KB alias.py 690B pics 
edge_list.png 26KB deepctrbot.png 21KB code.png 29KB weichennote.png 69KB .gitignore 1KB README.md 6KB资源评论
