Skip to content

Latest commit

 

History

History
107 lines (86 loc) · 4.8 KB

README.md

File metadata and controls

107 lines (86 loc) · 4.8 KB
Raw

GraphEmbedding

Method

Model Paper Note
DeepWalk [KDD 2014]DeepWalk: Online Learning of Social Representations 【Graph Embedding】DeepWalk：算法原理，实现和应用
LINE [WWW 2015]LINE: Large-scale Information Network Embedding 【Graph Embedding】LINE：算法原理，实现和应用
Node2Vec [KDD 2016]node2vec: Scalable Feature Learning for Networks 【Graph Embedding】Node2Vec：算法原理，实现和应用
SDNE [KDD 2016]Structural Deep Network Embedding 【Graph Embedding】SDNE：算法原理，实现和应用
Struc2Vec [KDD 2017]struc2vec: Learning Node Representations from Structural Identity 【Graph Embedding】Struc2Vec：算法原理，实现和应用

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
python setup.py install
cd examples
python deepwalk_wiki.py

DisscussionGroup & Related Projects

公众号：浅梦的学习笔记

 微信：deepctrbot

Usage

The design and implementation follows simple principles(graph in,embedding out) as much as possible.

Input format

we use networkxto create graphs.The input of networkx graph is as follows: node1 node2 <edge_weight>

DeepWalk

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

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

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

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

G = nx.read_edgelist('../data/flight/brazil-airports.edgelist',create_using=nx.DiGraph(),nodetype=None,data=[('weight',int)])#read graph

model = 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