GitHub Code | MinCut Pooling | 预训练|图上的自监督学习

Posted 2021-03-31 DrugAI

本专栏收集GitHub最近的更新的图网络相关代码合集，也有可能是很早之前的研究工作，最近有新的更新。至于GitHub根据什么算法推荐，小编暂时不清楚~如果你也觉得有用，欢迎转发给需要的小伙伴，另外有相关工作需要宣传也欢迎与小编联系~

1. Spectral Clustering with Graph Neural Networks for Graph Pooling ICML2020

---

This code reproduces the experimental results obtained with the MinCutPool layer as presented in the ICML 2020 paper

Spectral Clustering with Graph Neural Networks for Graph Pooling
F. M. Bianchi*, D. Grattarola*, C. Alippi

The official implementation of the MinCutPool layer can be found in Spektral.

An implementation of MinCutPool for PyTorch is also available in Pytorch Geometric.

https://github.com/FilippoMB/Spectral-Clustering-with-Graph-Neural-Networks-for-Graph-Pooling

该工作发表在ICML2020, 主要是通过最小割的方式方式进行pooling，优点是可导不需要谱分解，在Image分割，图分类，聚类上取得很好的结果~

2. Strategies for Pre-training Graph Neural Networks ICLR2020

---

This is a Pytorch implementation of the following paper:

Weihua Hu*, Bowen Liu*, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, Jure Leskovec. Strategies for Pre-training Graph Neural Networks. ICLR 2020. arXiv OpenReview

If you make use of the code/experiment in your work, please cite our paper (Bibtex below).

 
   
   
 

  
    
    
  @inproceedings{
hu2020pretraining,
title={Strategies for Pre-training Graph Neural Networks},
author={Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay Pande, Jure Leskovec},
booktitle={International Conference on Learning Representations},
year={2020},
url={https://openreview.net/forum?id=HJlWWJSFDH},
 
   
   
 

论文发表在ICLR2020, 这篇论文提出了一系列的预训练的方法，代码已经开源

相关解读

3. When Does Self-Supervision Help Graph Convolutional Networks? ICML2020

---

PyTorch code for When Does Self-Supervision Help Graph Convolutional Networks? [supplement]

Yuning You*, Tianlong Chen*, Zhangyang Wang, Yang Shen

In ICML 2020.

Overview

Properly designed multi-task self-supervision benefits GCNs in gaining more generalizability and robustness. In this repository we verify it through performing experiments on several GCN architectures with three designed self-supervised tasks: node clustering, graph partitioning and graph completion.

这篇论文非常有意思，小编后续会继续跟踪，这里先标记一下。该工作主要是通过设计三种自监督的任务：聚类，分割，补充学习更有泛化性和鲁棒性的图表示。