图神经网络构建代码
# GPF
## 一、GPF（Graph Processing Flow）：利用图神经网络处理问题的一般化流程
1、图节点预表示：利用NE框架，直接获得全图每个节点的Embedding;
2、正负样本采样：（1）单节点样本；（2）节点对样本；
3、抽取封闭子图：可做类化处理，建立一种通用图数据结构;
4、子图特征融合：预表示、节点特征、全局特征、边特征;
5、网络配置：可以是图输入、图输出的网络；也可以是图输入，分类/聚类结果输出的网络;
6、训练和测试;
## 二、主要文件：
1、graph.py：读入图数据;
2、embeddings.py：预表示学习;
3、sample.py：采样;
4、subgraphs.py/s2vGraph.py：抽取子图;
5、batchgraph.py：子图特征融合;
6、classifier.py：网络配置;
7、parameters.py/until.py:参数配置/帮助文件;
## 三、使用
1、在parameters.py中配置相关参数（可默认）；
2、在example/文件夹中运行相应的案例文件--包括链接预测、节点状态预测；
以链接预测为例：
### 1、导入配置参数
```from parameters import parser, cmd_embed, cmd_opt```
### 2、参数转换
```
args = parser.parse_args()
args.cuda = not args.noCuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
if args.cuda:
torch.cuda.manual_seed(args.seed)
if args.hop != 'auto':
args.hop = int(args.hop)
if args.maxNodesPerHop is not None:
args.maxNodesPerHop = int(args.maxNodesPerHop)
```
### 3、读取数据
```
g = graph.Graph()
g.read_edgelist(filename=args.dataName, weighted=args.weighted, directed=args.directed)
g.read_node_status(filename=args.labelName)
```
### 4、获取全图节点的Embedding
```
embed_args = cmd_embed.parse_args()
embeddings = embeddings.learn_embeddings(g, embed_args)
node_information = embeddings
#print node_information
```
### 5、正负节点采样
```
train, train_status, test, test_status = sample.sample_single(g, args.testRatio, max_train_num=args.maxTrainNum)
```
### 6、抽取节点对的封闭子图
```
net = until.nxG_to_mat(g)
#print net
train_graphs, test_graphs, max_n_label = subgraphs.singleSubgraphs(net, train, train_status, test, test_status, args.hop, args.maxNodesPerHop, node_information)
print('# train: %d, # test: %d' % (len(train_graphs), len(test_graphs)))
```
### 7、加载网络模型，并在classifier中配置相关参数
```
cmd_args = cmd_opt.parse_args()
cmd_args.feat_dim = max_n_label + 1
cmd_args.attr_dim = node_information.shape[1]
cmd_args.latent_dim = [int(x) for x in cmd_args.latent_dim.split('-')]
if len(cmd_args.latent_dim)
文件下载
资源详情
[{"title":"（ 80 个子文件 119KB ） 图神经网络构建代码","children":[{"title":"GPF-master","children":[{"title":".gitignore <span style='color:#111;'> 1.17KB </span>","children":null,"spread":false},{"title":"GPF","children":[{"title":"data","children":[{"title":"Testdata.ipynb <span style='color:#111;'> 3.31KB </span>","children":null,"spread":false},{"title":"USAir.edgeList.txt <span style='color:#111;'> 15.84KB </span>","children":null,"spread":false},{"title":"karate.label.txt <span style='color:#111;'> 159B </span>","children":null,"spread":false},{"title":"USAir.mat <span style='color:#111;'> 5.09KB </span>","children":null,"spread":false},{"title":"USAir.label.txt <span style='color:#111;'> 1.84KB </span>","children":null,"spread":false},{"title":"karate.edgelist.txt <span style='color:#111;'> 389B </span>","children":null,"spread":false}],"spread":true},{"title":"GraphNet","children":[{"title":"pscn.py <span style='color:#111;'> 2.64KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"s2v_lib.py <span style='color:#111;'> 6.18KB </span>","children":null,"spread":false},{"title":"s2v_lib","children":[{"title":"mlp.py <span style='color:#111;'> 1.67KB </span>","children":null,"spread":false},{"title":"embedding.py <span style='color:#111;'> 4.74KB </span>","children":null,"spread":false},{"title":"Makefile <span style='color:#111;'> 825B </span>","children":null,"spread":false},{"title":"src","children":[{"title":"lib","children":[{"title":"config.cpp <span style='color:#111;'> 51B </span>","children":null,"spread":false},{"title":"graph_struct.cpp <span style='color:#111;'> 1.69KB </span>","children":null,"spread":false},{"title":"msg_pass.cpp <span style='color:#111;'> 2.68KB </span>","children":null,"spread":false}],"spread":true},{"title":"s2v_lib.cpp <span style='color:#111;'> 3.61KB </span>","children":null,"spread":false}],"spread":true},{"title":"build","children":[{"title":"dll","children":[{"title":"libs2v.d <span style='color:#111;'> 160B </span>","children":null,"spread":false},{"title":"libs2v.so <span style='color:#111;'> 32.46KB </span>","children":null,"spread":false}],"spread":false},{"title":"lib","children":[{"title":"config.o <span style='color:#111;'> 2.05KB </span>","children":null,"spread":false},{"title":"graph_struct.o <span style='color:#111;'> 15.05KB </span>","children":null,"spread":false},{"title":"config.d <span style='color:#111;'> 56B </span>","children":null,"spread":false},{"title":"msg_pass.d <span style='color:#111;'> 105B </span>","children":null,"spread":false},{"title":"graph_struct.d <span style='color:#111;'> 74B </span>","children":null,"spread":false},{"title":"msg_pass.o <span style='color:#111;'> 8.88KB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"s2v_lib.py <span style='color:#111;'> 6.16KB </span>","children":null,"spread":false},{"title":"include","children":[{"title":"msg_pass.h <span style='color:#111;'> 453B </span>","children":null,"spread":false},{"title":"config.h <span style='color:#111;'> 657B </span>","children":null,"spread":false},{"title":"s2v_lib.h <span style='color:#111;'> 847B </span>","children":null,"spread":false},{"title":"graph_struct.h <span style='color:#111;'> 2.60KB </span>","children":null,"spread":false}],"spread":false},{"title":"pytorch_util.py <span style='color:#111;'> 1.81KB </span>","children":null,"spread":false}],"spread":true},{"title":"gat.py <span style='color:#111;'> 2.17KB </span>","children":null,"spread":false},{"title":"gcn_layers.py <span style='color:#111;'> 1.22KB </span>","children":null,"spread":false},{"title":"pytorch_util.py <span style='color:#111;'> 1.81KB </span>","children":null,"spread":false},{"title":"gcn.py <span style='color:#111;'> 1.83KB </span>","children":null,"spread":false},{"title":"mlp_dropout.py <span style='color:#111;'> 1.94KB </span>","children":null,"spread":false},{"title":"DGCNN.py <span style='color:#111;'> 5.68KB </span>","children":null,"spread":false},{"title":"gat_layers.py <span style='color:#111;'> 3.61KB </span>","children":null,"spread":false}],"spread":false},{"title":"src","children":[{"title":"classifier.py <span style='color:#111;'> 4.95KB </span>","children":null,"spread":false},{"title":"subgraphs.py <span style='color:#111;'> 10.79KB </span>","children":null,"spread":false},{"title":"sample.py <span style='color:#111;'> 2.24KB </span>","children":null,"spread":false},{"title":"batchgraph.py <span style='color:#111;'> 1.86KB </span>","children":null,"spread":false},{"title":"graph.py <span style='color:#111;'> 3.30KB </span>","children":null,"spread":false},{"title":"Parameters.py <span style='color:#111;'> 8.08KB </span>","children":null,"spread":false},{"title":"s2vGraph.py <span style='color:#111;'> 1.22KB </span>","children":null,"spread":false},{"title":"main_pairs.py <span style='color:#111;'> 2.43KB </span>","children":null,"spread":false},{"title":"main_single.py <span style='color:#111;'> 2.50KB </span>","children":null,"spread":false},{"title":"main_fixDegree.py <span style='color:#111;'> 2.51KB </span>","children":null,"spread":false},{"title":"embeddings.py <span style='color:#111;'> 3.56KB </span>","children":null,"spread":false},{"title":"until.py <span style='color:#111;'> 600B </span>","children":null,"spread":false}],"spread":false},{"title":"example","children":[{"title":"main_pairs.py <span style='color:#111;'> 2.48KB </span>","children":null,"spread":false},{"title":"main_single.py <span style='color:#111;'> 2.55KB </span>","children":null,"spread":false},{"title":"main_fixDegree.py <span style='color:#111;'> 2.56KB </span>","children":null,"spread":false}],"spread":true},{"title":"readme.txt <span style='color:#111;'> 776B </span>","children":null,"spread":false},{"title":"NE","children":[{"title":"sdne.py <span style='color:#111;'> 11.27KB </span>","children":null,"spread":false},{"title":"gcn","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"layers.py <span style='color:#111;'> 5.75KB </span>","children":null,"spread":false},{"title":"models.py <span style='color:#111;'> 6.21KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 5.31KB </span>","children":null,"spread":false},{"title":"metrics.py <span style='color:#111;'> 691B </span>","children":null,"spread":false},{"title":"gcnAPI.py <span style='color:#111;'> 6.73KB </span>","children":null,"spread":false},{"title":"gcn.py <span style='color:#111;'> 6.73KB </span>","children":null,"spread":false},{"title":"inits.py <span style='color:#111;'> 810B </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 3.90KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"hope.py <span style='color:#111;'> 1.61KB </span>","children":null,"spread":false},{"title":"gf.py <span style='color:#111;'> 2.48KB </span>","children":null,"spread":false},{"title":"lap.py <span style='color:#111;'> 1.77KB </span>","children":null,"spread":false},{"title":"graph.py <span style='color:#111;'> 3.37KB </span>","children":null,"spread":false},{"title":"grarep.py <span style='color:#111;'> 2.26KB </span>","children":null,"spread":false},{"title":"__main__.py <span style='color:#111;'> 8.40KB </span>","children":null,"spread":false},{"title":"walker.py <span style='color:#111;'> 5.98KB </span>","children":null,"spread":false},{"title":"node2vec.py <span style='color:#111;'> 1.56KB </span>","children":null,"spread":false},{"title":"line.py <span style='color:#111;'> 10.81KB </span>","children":null,"spread":false},{"title":"classify.py <span style='color:#111;'> 3.10KB </span>","children":null,"spread":false},{"title":"lle.py <span style='color:#111;'> 1.72KB </span>","children":null,"spread":false},{"title":"tadw.py <span style='color:#111;'> 4.27KB </span>","children":null,"spread":false}],"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 6.30KB </span>","children":null,"spread":false},{"title":"gpf.JPG <span style='color:#111;'> 19.66KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]
评论信息
其他资源
- PPL锁相环matlab
- 新闻分类（文本分类）
- project案例项目管理实验报告——本科生
- 查找两幅图中不同
- 时间序列分析—基于R，王燕，全文有目录
- 一种基于ADS 优化的微带带通滤波器设计及实现
- 华为项目管理10大模板Excel版(可直接套用)
- jsp书店租赁管理系统
- 软件工程经济学 关联矩阵法 程序.zip
- 智能水滴改进算法
- red5 windows版本
- Ruby编程语言.pdf
- PLO编译器的扩展（编译原理课程实践）
- mqtt的android端jar包
- lm-social-bias-源码
- 朴素贝叶斯分类.pptx
- python最新版本
- C++数值排序
- 图书管理系统
- os课程设计 操作系统课程设计
- 专业虚拟DJ台7.0中文版
- javaweb Excel生成器
- 移远BC95资料 NB-IoT资料
免责申明
【只为小站】的资源来自网友分享，仅供学习研究，请务必在下载后24小时内给予删除，不得用于其他任何用途，否则后果自负。基于互联网的特殊性，【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查；无论 【只为小站】 经营者是否已进行审查，用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明