Light

chengtaicao / meta-gnn Goto Github PK

View Code? Open in Web Editor NEW

53.0 2.0 13.0 541 KB

Python 100.00%

meta-gnn's Introduction

Meta-GNN: On Few-shot Node Classification in Graph Meta-learning

Authors:

[Fan Zhou]
Chengtai Cao
[Kunpeng Zhang]
[Goce Trajcevski]
[Ting Zhong]
[Ji Geng]

Desccription of Meta-GNN

source_code for Meta-GNN (implement of Meta-GNN): Meta-GNN: On Few-shot Node Classification in Graph Meta-learning

Environment And Dependencies

PyTorch>=1.0.0
Install other dependencies: $ pip install -r requirement.txt

Dataset

We provide the citation network datasets under meta_gnn/data/.

Dataset Partition

We have shown the details of node partition in the paper.

Usage

For Meta-GNN:

$ cd meta_gnn/
$ python sgc.py

For Few-shot:
(1)SGC:

$ cd sgc_fewshot/
$ python citation.py

(2)GCN:

$ cd gcn_fewshot/
$ python citation.py

(3)Deepwalk or Node2Vec:

$ cd graph_embedding_fewshot/
$ python deepwalk.py    //    $ python node2vec.py

(4)Graphsage

$ cd graphsage_fewshot/
$ python graphsage.py --dataset cora --gpu 0

Reference

Any comments and feedback are appreciated.

meta-gnn's People

Contributors

Stargazers

Watchers

Forkers

serenaquinn leozhang97 aslandery yjwtheonly zhen-tan-dmml marooncabbage jacobhuangchina crystal22 shane995 liuqiangh scottymz piiikiu h74546

meta-gnn's Issues

Meta_gnn has 0 training accuracy and 0 testing accuracy

When I ran the sgc.py in the meta_gnn folder, I found both the training accuracy and testing accuracy are 0 in all cases.

Meta-GNN Learner does not have the GCN layer code?

Thanks for open-sourcing!

I am learning your code and I couldn't find the code for GNN learner in the learner.py class in the meta GNN folder, it looks like it only uses the linear layer. I am wondering could you point it to me where the GCN layer is used for the base learner class?

Thank you!

Meta-data generate problem

According to your code, when generating a meta task, no matter what the n-way is, it will generate a 2-way data.

accuracy meaning

Dear Authors,
May I ask about accuracy from your codes
Step: 0 Meta_Training_Accuracy: [0.25833333 0.34166667 0.41666667 0.45 0.46666667 0.50833333
0.54166667 0.55833333 0.6 0.64166667 0.675 ]
why the length of list is 1+update_step and what is the meaning of each acc[i]?
how I evaluate the model is good or not from accuracy?
thanks,

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.