Coder Social home page Coder Social logo

malllabiisc / hypergcn Goto Github PK

View Code? Open in Web Editor NEW
174.0 4.0 28.0 10.98 MB

NeurIPS 2019: HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs

License: Apache License 2.0

Python 100.00%
graph-convolutional-network hypergraph semi-supervised-learning

hypergcn's People

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar

Forkers

ccfbupt jaringau songfgh ammieqi karkun-garuvi-yiyal sunshine8586 o7s8r6 freekang youjibiying stsoor dcmmc jiamingz1996 mengkunzhao yhjiujiu sohailkhanmarwat sparsel minhzou guodanqi yeongukang krickpp moguizhizi summer-sea meredith92 lilit427 wjj0122 xingye1999 fladmark luoyuanlab

hypergcn's Issues

About Cora dataset and Citeseer dataset

Hello, your work is very good and very valuable for research. Can you provide the Cora dataset and Citeseer dataset that you have processed in the paper?

Dataset splits

First question: Can you please provide with the code to produce the hypergraph dataset from the original graph data?
Second question: what are the train/test split sizes?

Question about results on DBLP

Hi,

Thanks for the excellent work. I see that you've released the DBLP data. When I directly run hypergcn.py (by setting mediators = True), however, the test error I obtained is around 30, which does not match the results in the paper (Table 4). When I change the learning rate to 0.1, the test error can be reduced to about 13, but this is still not the test error reported in the paper. Did I make any mistake?

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.