Light

xptree / netmf Goto Github PK

View Code? Open in Web Editor NEW

186.0 9.0 47.0 1.19 MB

Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec

License: MIT License

Python 100.00%

social-network social-network-analysis network-embedding matrix-factorization deepwalk node2vec

netmf's Introduction

NetMF

This is a Python implementation of NetMF for the task of network embedding learning, as described in our paper:

Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec

Data Sets

BlogCatalog Source Preprocessed

Protein-Protein Interaction Source Preprocessed

Wikipedia Source Preprocessed

Flickr

Cite

Please cite our paper if you use this code in your own work:

@inproceedings{qiu2018network,
  title={Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec},
  author={Qiu, Jiezhong and Dong, Yuxiao and Ma, Hao and Li, Jian and Wang, Kuansan and Tang, Jie},
  booktitle={Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining},
  pages={459--467},
  year={2018},
  organization={ACM}
}

netmf's People

Contributors

Stargazers

Watchers

Forkers

xiaoliang008 daniel-tan zshwuhan drpengsong zhouyonglong colinsongf bokunwang liqipap raymondhliu gangwu001 mahmud83 daiquanyu songfgh xishizhaoz hhh920406 yangchunm jufangshen locussam xy1234552 tyut2018 xuyou314 krithikamurugesan gaiyu0 huabeixiaobai chaolirv pwforks archernero liuchuang0059 cthoyt-forks-and-packages freemanguohua hanbei969 mythwn simba2017 xiaoanshi tsourolampis xitongsystem baobunuo qianrenjian baibingbit koame shuowang-ai tlarock 123carmen ghostintheshellarise hashingcoder calypsoidea

netmf's Issues

Make installable with pip

It would be nice to be able to pip install this code, maybe even from PyPI.

reason for returning S_d \sqrt(\Sigma_d) as the network embedding

Thanks for sharing the code. I'm curious about why after obtaining the approximated deepwalk matrix (after max(x, 1) and taking log), in the last step of NetMF, it is $$U_d \sqrt(\Sigma_d)$$ from SVD that is returned as the final embedding? The paper doesn't seem to justify the benefit of this instead of some other embedding.

How to scale up to big data?

Thanks for the great paper. I would like to use it on a specific application with big data, yet it fails in the middle of the computations due to memory issues. Do you have any suggestions on how to improve the code to be applicable to adjacency matrices of million nodes?

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.