tf-gnn-samples:图神经网络的TensorFlow实现
TF图神经网络样本
该存储库是代码版本，对应于介绍具有特征线性调制的图神经网络（GNN）的文章（ ）。 在本文中，讨论了许多GNN架构：
门控图神经网络（GGNN）（ ）。
关系图卷积网络（RGCN）（ ）。
关系图注意力网络（RGAT）-图注意力网络（ ）对几种边缘类型的概括。
关系图同构网络（RGIN）-图同构网络（ ）对几种边缘类型的概括。
带有边缘MLP的图形神经网络（GNN-Edge-MLP）-RGCN的一种变体，其中边缘上的消息是使用完整MLP而非单个层来计算的。
关系图动态卷积网络（RGDCN）-RGCN的新变体，其中动态计算卷积层的权重。
具特征线性调制（GNN-FiLM）的图形神经网络-带有FiLM层的RGCN的新扩展。
本文中提出的结果基于该存储库中提供的模型和任务的实现。
此代码已在使用TensorFlow 1.13.1的Python 3.
文件下载
资源详情
[{"title":"（ 65 个子文件 25.7MB ） tf-gnn-samples:图神经网络的TensorFlow实现","children":[{"title":"tf-gnn-samples-master","children":[{"title":"models","children":[{"title":"rgin_model.py <span style='color:#111;'> 1.92KB </span>","children":null,"spread":false},{"title":"rgcn_model.py <span style='color:#111;'> 1.63KB </span>","children":null,"spread":false},{"title":"sparse_graph_model.py <span style='color:#111;'> 18.82KB </span>","children":null,"spread":false},{"title":"gnn_film_model.py <span style='color:#111;'> 1.61KB </span>","children":null,"spread":false},{"title":"gnn_edge_mlp_model.py <span style='color:#111;'> 1.87KB </span>","children":null,"spread":false},{"title":"ggnn_model.py <span style='color:#111;'> 1.68KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 322B </span>","children":null,"spread":false},{"title":"rgdcn_model.py <span style='color:#111;'> 1.96KB </span>","children":null,"spread":false},{"title":"rgat_model.py <span style='color:#111;'> 1.51KB </span>","children":null,"spread":false}],"spread":true},{"title":"run_varmisuse_benchs.py <span style='color:#111;'> 4.17KB </span>","children":null,"spread":false},{"title":"tasks","children":[{"title":"ppi_task.py <span style='color:#111;'> 12.74KB </span>","children":null,"spread":false},{"title":"sparse_graph_task.py <span style='color:#111;'> 9.83KB </span>","children":null,"spread":false},{"title":"default_hypers","children":[{"title":"VarMisuse_GNN-FiLM.json <span style='color:#111;'> 929B </span>","children":null,"spread":false},{"title":"PPI_GNN-Edge-MLP1.json <span style='color:#111;'> 227B </span>","children":null,"spread":false},{"title":"VarMisuse_RGIN.json <span style='color:#111;'> 979B </span>","children":null,"spread":false},{"title":"PPI_RGIN.json <span style='color:#111;'> 363B </span>","children":null,"spread":false},{"title":"VarMisuse_RGAT.json <span style='color:#111;'> 849B </span>","children":null,"spread":false},{"title":"QM9_RGCN.json <span style='color:#111;'> 779B </span>","children":null,"spread":false},{"title":"QM9_GNN-FiLM.json <span style='color:#111;'> 825B </span>","children":null,"spread":false},{"title":"VarMisuse_RGCN.json <span style='color:#111;'> 831B </span>","children":null,"spread":false},{"title":"PPI_GGNN.json <span style='color:#111;'> 228B </span>","children":null,"spread":false},{"title":"QM9_GNN-Edge-MLP0.json <span style='color:#111;'> 950B </span>","children":null,"spread":false},{"title":"QM9_GNN-Edge-MLP1.json <span style='color:#111;'> 948B </span>","children":null,"spread":false},{"title":"PPI_GNN-FiLM.json <span style='color:#111;'> 227B </span>","children":null,"spread":false},{"title":"PPI_GNN-Edge-MLP0.json <span style='color:#111;'> 227B </span>","children":null,"spread":false},{"title":"VarMisuse_GNN-Edge-MLP1.json <span style='color:#111;'> 998B </span>","children":null,"spread":false},{"title":"VarMisuse_GNN-Edge-MLP0.json <span style='color:#111;'> 997B </span>","children":null,"spread":false},{"title":"VarMisuse_GGNN.json <span style='color:#111;'> 916B </span>","children":null,"spread":false},{"title":"QM9_GGNN.json <span style='color:#111;'> 806B </span>","children":null,"spread":false},{"title":"QM9_RGAT.json <span style='color:#111;'> 750B </span>","children":null,"spread":false},{"title":"PPI_RGCN.json <span style='color:#111;'> 228B </span>","children":null,"spread":false},{"title":"QM9_RGIN.json <span style='color:#111;'> 999B </span>","children":null,"spread":false},{"title":"PPI_RGAT.json <span style='color:#111;'> 228B </span>","children":null,"spread":false}],"spread":false},{"title":"qm9_task.py <span style='color:#111;'> 13.95KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 221B </span>","children":null,"spread":false},{"title":"citation_network_task.py <span style='color:#111;'> 8.28KB </span>","children":null,"spread":false},{"title":"varmisuse_task.py <span style='color:#111;'> 26.76KB </span>","children":null,"spread":false}],"spread":true},{"title":"data","children":[{"title":"qm9","children":[{"title":"test.jsonl.gz <span style='color:#111;'> 1.97MB </span>","children":null,"spread":false},{"title":"valid.jsonl.gz <span style='color:#111;'> 1.97MB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 7.05KB </span>","children":null,"spread":false},{"title":"train.jsonl.gz <span style='color:#111;'> 21.69MB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"test.py <span style='color:#111;'> 1.85KB </span>","children":null,"spread":false},{"title":"run_qm9_benchs.py <span style='color:#111;'> 3.19KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 4.57KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.13KB </span>","children":null,"spread":false},{"title":"CONTRIBUTING.md <span style='color:#111;'> 916B </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 53B </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.15KB </span>","children":null,"spread":false},{"title":"run_ppi_benchs.py <span style='color:#111;'> 2.51KB </span>","children":null,"spread":false},{"title":"reorg_varmisuse_data.sh <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 14.25KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"model_utils.py <span style='color:#111;'> 2.92KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 5.03KB </span>","children":null,"spread":false},{"title":"citation_network_utils.py <span style='color:#111;'> 5.25KB </span>","children":null,"spread":false},{"title":"varmisuse_data_splitter.py <span style='color:#111;'> 3.56KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 117B </span>","children":null,"spread":false}],"spread":false},{"title":".flake8 <span style='color:#111;'> 126B </span>","children":null,"spread":false},{"title":"gnns","children":[{"title":"gnn_edge_mlp.py <span style='color:#111;'> 6.05KB </span>","children":null,"spread":false},{"title":"rgdcn.py <span style='color:#111;'> 9.33KB </span>","children":null,"spread":false},{"title":"gnn_film.py <span style='color:#111;'> 6.52KB </span>","children":null,"spread":false},{"title":"ggnn.py <span style='color:#111;'> 4.62KB </span>","children":null,"spread":false},{"title":"rgat.py <span style='color:#111;'> 7.65KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 278B </span>","children":null,"spread":false},{"title":"rgin.py <span style='color:#111;'> 7.00KB </span>","children":null,"spread":false},{"title":"rgcn.py <span style='color:#111;'> 5.95KB </span>","children":null,"spread":false}],"spread":false}],"spread":false}],"spread":true}]
评论信息
其他资源
- 短时傅立叶变换 Wigner-Ville分布 小波变换
- 2021北京邮电大学考研通原雪山灰虎-习题汇编.pdf
- 一维条形码的生成与实现（c语言+注释）
- 北京市1935-2018年气象数据
- 软件工程案例(图书管理系统)需求分析
- 数据库系统教程 王能斌（下册）
- 新标准C++程序设计教材11-20章课后题答案
- 实时录音并显示波形.zip
- zynq/zedboard/xlinx 学习例程及笔记
- [6] OFDM链路的误码率和OFDM符号的功率谱密度-附件资源
- 2021年春节假期大数据洞察报告.pdf
- 通信信号识别的经典matlab仿真
- 视频文件播放.zip
- 简约商务-科技-动态PPT模板.pptx
- 冲刺日语N1 每天一小段阅读 附翻译.pdf
- 量子保密通信技术进展及应用趋势分析.pdf
- Internet of Things Security Principles and Practice 9789811599415.zip
- 神经网络专家系统在电机故障诊断中的应用
- spark知识点整理.docx
- Ubuntu学习资料
- 通过 Java 获取音频的波形图
- 树的实现--利用二叉链表（孩子-兄弟）存储结构
- 数字图像处理论文——米粒
- libsvm3.14
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