Light

hjjpku / attention_in_graph Goto Github PK

View Code? Open in Web Editor NEW

37.0 5.0 15.0 76.53 MB

attention mechanism for graph classification, significant sub-graph mining, graph disstillation

Python 75.83% MATLAB 6.50% Makefile 1.45% C 1.00% C++ 10.53% Shell 4.69%

attention_in_graph's Introduction

This zip file contains source code and datasets for our ICCV19 paper “AttPool : Towards Hierarchical Feature Representation in Graph Convolutional Networks via Attention Mechanism”

To run our code, please follow the steps below:

Dependencies:

Pytorch >=1.0.0, Python >=3.5

Usage:

run pip3 install -r requirement.txt
We provide all datasets that have been mentioned in the paper for testing.
We provide shell scripts, for training baseline , AttPool-G and AttPool-L models with 10- fold cross validation on datasets, respectively. For example, to train AttPool-G on the NCI1 dataset, please run the shell script ./run_attpool_global_nci1.sh.
You can find the shell scripts for different datasets in the direcotry ./script

If you find our work useful, please consider citing:

@inproceedings{huang2019attpool,
	  title={AttPool: Towards Hierarchical Feature Representation in Graph Convolutional Networks via Attention Mechanism},
	    author={Huang, Jingjia and Li, Zhangheng and Li, Nannan and Liu, Shan and Li, Ge},
		  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
		    pages={6480--6489},
			  year={2019}
}

attention_in_graph's People

Contributors

Stargazers

Watchers

Forkers

ryfan-rs dlwbm123 nnu-gisa gnn2qsu bestyours ammieqi danieldng andrewcuho zoharli student4321 queenie88 liuchuang0059 mohan-isha luzelin ahwhbc

attention_in_graph's Issues

作者的交叉验证思路是哪种？

作者好，我看文中说使用10-fold交叉验证，但是不太懂文中如何做测试的，请问下是下面之一还是其他的思路吗

用这100k条数据做k-fold交叉验证，来调模型参数
先随机划分出70k条数据做训练集用来根据交叉验证调参数，调好之后再用剩下的30k条数据做测试集
其他？

请问下plot1.py文件的作用是什么？

在运行此文件后，输出下面的结果，请问下下面的结果是什么意思啊？
`
1 0.5559 0.0805 0.5559 0.5559 0.5559
max 0.555885
2 0.5559 0.0805 0.5559 0.5559 0.5559
max 0.555885
3 0.5559 0.0805 0.5500 0.5559 0.5559
max 0.555885
4 0.5529 0.0819 0.5618 0.5529 0.5559
max 0.555885
5 0.5588 0.0911 0.5706 0.5500 0.5470

...
`

请问一下如何运行diffpool模型

您好!我想用代码中的diffpool模型，但是我把sh文件中modal的值agcn换成diffpool时，运行.sh文件时程序卡着不出结果，非常困惑。

can't run your code

Hello, there is no code_ attpool_ global_ Nci1.sh file in your project. Can you upload it? Thank you.

表格1里的“AVG”具体是如何计算的

作者的思路很新颖，对此篇文章比较感兴趣，请问下实验里的表格1里的“AVG”具体是如何计算的呀？

no file :log/global_nci1/acc_results.txt

./run_attpool_global_nci1.sh
1
2
3
4
5
6
7
8
9
10
rm:

Unable to delete 'log/global_nci1/acc_results.txt': There is no such file or directory
max acc: 0.0000, epoch -1

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.