search

convexfi / spectralGraphTopology

Structured Graph Learning via Laplacian Spectral Constraints (NeurIPS 2019)
https://CRAN.R-project.org/package=spectralGraphTopology
GNU General Public License v3.0
59 stars 17 forks source link

python version #6

Open IssamLaradji opened 4 years ago

IssamLaradji commented 4 years ago

Great work! Will there be a python version?

Thanks!

mirca commented 4 years ago

@IssamLaradji Thanks! Likely!

IssamLaradji commented 4 years ago

pytorch version would probably be even better because then it would support GPU and automatic differentiation.

mirca commented 4 years ago

We actually don't need AD. The gradients we need are easily computable in closed-form. I think JAX would be the way to go due to JIT for GPU/TPU.

IssamLaradji commented 4 years ago

sounds good, thx.

anomic1911 commented 3 years ago

Hi @IssamLaradji, I have reimplemented SGL in python, it is still in progress though. In case you want to check out: https://github.com/anshul3899/Structured-Graph-Learning

IssamLaradji commented 3 years ago

looks amazing @anshul3899 , we can start testing on some applications, thanks!