gcn:在TensorFlow中实现图卷积网络-源码

上传者: 42139871 | 上传时间: 2021-05-28 23:59:54 | 文件大小: 5.07MB | 文件类型: ZIP
图卷积网络 这是图卷积网络的TensorFlow实现,用于图中节点的(半监督)分类任务,如我们的论文所述: Thomas N.Kipf,Max Welling,(ICLR 2017) 有关高级解释,请查看我们的博客文章: 托马斯·基普夫(Thomas Kipf),(2016) 安装 python setup.py install 要求 张量流(> 0.12) 网络 运行演示 cd gcn python train.py 数据 为了使用您自己的数据,您必须提供 N×N邻接矩阵(N是节点数), N×D特征矩阵(D是每个节点的特征数),以及 N by E二进制标签矩阵(E是类数)。 看一看在load_data()函数utils.py为例。 在此示例中,我们加载引文网络数据(Cora,Citeseer或Pubmed)。 原始数据集可以在以下位置找到: : 。 在我们的版本中(请参

文件下载

资源详情

[{"title":"( 36 个子文件 5.07MB ) gcn:在TensorFlow中实现图卷积网络-源码","children":[{"title":"gcn-master","children":[{"title":".gitignore <span style='color:#111;'> 1.09KB </span>","children":null,"spread":false},{"title":"LICENCE <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 3.04KB </span>","children":null,"spread":false},{"title":"gcn","children":[{"title":"models.py <span style='color:#111;'> 6.12KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 3.80KB </span>","children":null,"spread":false},{"title":"metrics.py <span style='color:#111;'> 691B </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 6.35KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 70B </span>","children":null,"spread":false},{"title":"layers.py <span style='color:#111;'> 5.75KB </span>","children":null,"spread":false},{"title":"data","children":[{"title":"ind.citeseer.allx <span style='color:#111;'> 581.08KB </span>","children":null,"spread":false},{"title":"ind.cora.graph <span style='color:#111;'> 58.44KB </span>","children":null,"spread":false},{"title":"ind.pubmed.x <span style='color:#111;'> 22.63KB </span>","children":null,"spread":false},{"title":"ind.citeseer.graph <span style='color:#111;'> 60.53KB </span>","children":null,"spread":false},{"title":"ind.cora.tx <span style='color:#111;'> 144.56KB </span>","children":null,"spread":false},{"title":"ind.citeseer.y <span style='color:#111;'> 2.94KB </span>","children":null,"spread":false},{"title":"ind.cora.allx <span style='color:#111;'> 251.27KB </span>","children":null,"spread":false},{"title":"ind.cora.y <span style='color:#111;'> 3.96KB </span>","children":null,"spread":false},{"title":"ind.citeseer.ty <span style='color:#111;'> 23.57KB </span>","children":null,"spread":false},{"title":"ind.citeseer.test.index <span style='color:#111;'> 4.88KB </span>","children":null,"spread":false},{"title":"ind.citeseer.tx <span style='color:#111;'> 254.22KB </span>","children":null,"spread":false},{"title":"ind.citeseer.ally <span style='color:#111;'> 54.32KB </span>","children":null,"spread":false},{"title":"ind.pubmed.ally <span style='color:#111;'> 219.47KB </span>","children":null,"spread":false},{"title":"ind.cora.test.index <span style='color:#111;'> 4.88KB </span>","children":null,"spread":false},{"title":"ind.cora.ally <span style='color:#111;'> 46.83KB </span>","children":null,"spread":false},{"title":"ind.pubmed.test.index <span style='color:#111;'> 5.86KB </span>","children":null,"spread":false},{"title":"ind.pubmed.graph <span style='color:#111;'> 460.75KB </span>","children":null,"spread":false},{"title":"ind.cora.x <span style='color:#111;'> 21.60KB </span>","children":null,"spread":false},{"title":"ind.cora.ty <span style='color:#111;'> 27.48KB </span>","children":null,"spread":false},{"title":"ind.pubmed.ty <span style='color:#111;'> 11.85KB </span>","children":null,"spread":false},{"title":"ind.citeseer.x <span style='color:#111;'> 30.36KB </span>","children":null,"spread":false},{"title":"ind.pubmed.y <span style='color:#111;'> 854B </span>","children":null,"spread":false},{"title":"ind.pubmed.allx <span style='color:#111;'> 7.23MB </span>","children":null,"spread":false},{"title":"ind.pubmed.tx <span style='color:#111;'> 396.00KB </span>","children":null,"spread":false}],"spread":false},{"title":"inits.py <span style='color:#111;'> 791B </span>","children":null,"spread":false}],"spread":true},{"title":"requirements.txt <span style='color:#111;'> 79B </span>","children":null,"spread":false},{"title":"setup.py <span style='color:#111;'> 625B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]

评论信息

  • panbaoran913 :
    请问,有没有简单的gcn的搭建方法嘛?必须要从layer.Dense,到Model,再到gcn,统统搭建一边嘛?还有就是我可以直接复制的代码过去,有效嘛
    2021-10-23

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