Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Online NMF #132

Closed
piskvorky opened this issue Oct 25, 2013 · 6 comments
Closed

Online NMF #132

piskvorky opened this issue Oct 25, 2013 · 6 comments
Assignees
Labels
difficulty hard Hard issue: required deep gensim understanding & high python/cython skills feature Issue described a new feature wishlist Feature request

Comments

@piskvorky
Copy link
Owner

Implement online non-negative matrix factorization from http://www.cs.cornell.edu/~chenhao/pub/online-NMF.pdf

@piskvorky
Copy link
Owner Author

@larsmans added a nice (but non-scalable) NMF implementation to scikit-learn. Get inspiration/help from there, too: scikit-learn/scikit-learn#2537

@larsmans
Copy link
Contributor

Actually the NMF in scikit-learn is mostly @vene's work, I just optimized it.

There's been some talk about coordinate descent algorithms for NMF in scikit-learn.

@souravsingh
Copy link
Contributor

@piskvorky I would like to work on the issue

@tmylk
Copy link
Contributor

tmylk commented Oct 19, 2016

Hi @souravsingh the best way to proceed is to apply to the RaRe incubator programme https://rare-technologies.com/incubator

@vene
Copy link

vene commented Oct 19, 2016

Hi,

Couple of notes:

  1. the NMF implementation in scikit-learn has been replaced by a more scalable coordinate descent-based one a couple of releases ago (but it's not online/out-of-core)
  2. you might be interested in libmf (paper) which supports online parallel NMF among others.

@menshikh-iv menshikh-iv added feature Issue described a new feature difficulty hard Hard issue: required deep gensim understanding & high python/cython skills labels Oct 3, 2017
@manojpandey
Copy link
Contributor

Took this up, working with @menshikh-iv 😄

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
difficulty hard Hard issue: required deep gensim understanding & high python/cython skills feature Issue described a new feature wishlist Feature request
Projects
None yet
Development

No branches or pull requests

8 participants