Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/shenweichen/GraphEmbedding
Implementation and experiments of graph embedding algorithms.
https://github.com/shenweichen/GraphEmbedding
deepwalk graph graphembedding line node2vec sdne struc2vec
Last synced: 4 months ago
JSON representation
Implementation and experiments of graph embedding algorithms.
- Host: GitHub
- URL: https://github.com/shenweichen/GraphEmbedding
- Owner: shenweichen
- License: mit
- Created: 2019-02-11T16:27:20.000Z (about 6 years ago)
- Default Branch: master
- Last Pushed: 2024-03-14T09:28:18.000Z (11 months ago)
- Last Synced: 2024-10-29T15:31:13.570Z (4 months ago)
- Topics: deepwalk, graph, graphembedding, line, node2vec, sdne, struc2vec
- Language: Python
- Homepage:
- Size: 665 KB
- Stars: 3,706
- Watchers: 63
- Forks: 994
- Open Issues: 44
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-python-machine-learning-resources - GitHub - 59% open · ⏱️ 21.06.2022): (图数据处理)
- awesome-list - GraphEmbedding - Implementation and experiments of graph embedding algorithms. (Graph / Others)
- StarryDivineSky - shenweichen/GraphEmbedding
README
# 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
公众号：浅梦学习笔记
微信：deepctrbot
# 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 `
## 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
```