Coder Social home page Coder Social logo

gat's Introduction

Pytorch Implementation of GCN & GAT

Pytorch Implementations of Semi-Supervised Classification with Graph Convolutional Networks and Graph Attention Networks.

image Overview of GAT.

Results

<Cora dataset>

Training Time Loss Acc
GCN 2s 0.9790 81.6%
GAT 17m 0.6724 83.8%
spGCN 13s 0.9215 81.4%
spGAT 1m30s 0.6745 84.7%

<Siteseer dataset>

Training Time Loss Acc
GCN 2s 1.2088 60%
GAT 21m 1.1907 59.1%
spGCN 17s 1.602 58.3%
spGAT 1m47s 1.1591 59.2%

GAT achieves better performances compared to GCN.

Usage

python3 train.py --model {gcn, gat, spgcn, spgat}

References

https://github.com/tkipf/pygcn https://github.com/Diego999/pyGAT

gat's People

Contributors

63days avatar seohuibae avatar

Stargazers

 avatar  avatar  avatar

Watchers

 avatar  avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

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

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

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

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.