[1] Deep Density Destructors

David I. Inouye 

Carnegie Mellon University

http://proceedings.mlr.press/v80/inouye18a/inouye18a.pdf

各方法对比总结如下

各方法效果对比如下

代码地址

https://github.com/davidinouye/destructive-deep-learning

---

              我是分割线

---

[2] Structured Control Nets for Deep Reinforcement Learning

Mario Srouji et al.

Carnegie Mellon University, Apple Inc.

http://proceedings.mlr.press/v80/srouji18a/srouji18a.pdf

本文所提网络结构如下

各方法效果对比如下

---

              我是分割线

---

[3] GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models

Jiaxuan You et al.

Stanford University, University of Southern California

http://proceedings.mlr.press/v80/you18a/you18a.pdf

GraphRNN 结构示例如下

算法伪代码如下

各方法结果对比如下

代码地址

https://github.com/JiaxuanYou/graph-generation

---

              我是分割线

---

[4] Kronecker Recurrent Units

Cijo Jose

Idiap Research Institute, Ecole Polytechnique F ´ ed´ erale ´ de Lausanne (EPFL),  Facebook AI Research

http://proceedings.mlr.press/v80/jose18a/jose18a.pdf

符号定义如下

各模型效果对比

---

              我是分割线

---

[5] NetGAN: Generating Graphs via Random Walks

Aleksandar Bojchevski et al.

Technical University of Munich

http://proceedings.mlr.press/v80/bojchevski18a/bojchevski18a.pdf

NetGAN效果对比如下

NetGAN结构示例如下

各方法效果对比如下

数据集统计如下

各方法效果对比如下

代码地址

https://github.com/danielzuegner/netgan

---

              我是分割线

---

[6] Stochastic Training of Graph Convolutional Networks with Variance 

Reduction

Jianfei Chen et al.

Tsinghua University, Georgia Institute of Technology, Ant Financial

http://proceedings.mlr.press/v80/chen18p/chen18p.pdf

各网络结构对比如下

各数据集统计如下

算法伪代码如下

各方法对比如下

各方法效果对比如下

代码地址

https: //github.com/thu-ml/stochastic_gcn

---

              我是分割线

---

您可能感兴趣