hibayesian / awesome-automl-papers Goto Github PK

Towards modular and programmable architecture search
Paper: https://arxiv.org/abs/1909.13404
Code: https://github.com/negrinho/deep_architect
Documentation: https://deep-architect.readthedocs.io/en/latest/

Techically, this is still DeepArchitect (but the old repo was renamed and now its here). This work extends the ideas in the original paper. The implementation is much more mature and supports arbitrary deep learning frameworks. We will maintain it and extend it going forward.

Thank you

NNI is an Microsoft Research open source AutoML toolkit for neural architecture search and hyper-parameter tuning, worthwhile for adding it into the project list:

https://github.com/Microsoft/nni

Thank you for taking the effort to maintain an updated list. Wish there was such a repo for other topics in ML too!

Have you looked at FAR-HO (https://github.com/lucfra/FAR-HO)? Its a gradient based algorithm - it'd be nice to have a section for gradient based algos.

Thank you again - hope you keep updating this list :)

Hi!

I think it will be good if this papers appear in your repository!

PROXYLESSNAS: DIRECT NEURAL ARCHITECTURE
SEARCH ON TARGET TASK AND HARDWARE

https://arxiv.org/abs/1812.00332

Bert-Sort refers to BERT-Sort: A Zero-shot MLM Semantic Encoder on Ordinal Features for AutoML, proposed by Mehdi Bahrami, et al.
I think it is a method for feature encoding, which is belong to Feature Engineering instead of Automated Feature Engineering. I guess that you put this paper under the Automated Feature Engineering because of the paper's title. It may be a mistake.

<> should be in the list, I think :)