Skip to main content

Neural Additive Models (PyTorch): Intepretable ML with Neural Nets

Project description

Neural Additive Models (PyTorch)

This is a PyTorch re-implementation for neural additive models, check out:

Neural Additive Model

Install Package

Dependencies

  • torch==1.7.0
  • fsspec==0.8.4
  • pandas==1.1.4
  • tqdm==4.54.0
  • sklearn==0.0
  • absl-py==0.11.0
  • gcsfs==0.7.1

Usage

conda env create -f environment.yml
conda activate nam-pt
python run.py

Citing

If you use this code in your research, please cite the following paper:

Agarwal, R., Frosst, N., Zhang, X., Caruana, R., & Hinton, G. E. (2020). Neural additive models: Interpretable machine learning with neural nets. arXiv preprint arXiv:2004.13912

  @article{agarwal2020neural,
    title={Neural additive models: Interpretable machine learning with neural nets},
    author={Agarwal, Rishabh and Frosst, Nicholas and Zhang, Xuezhou and
    Caruana, Rich and Hinton, Geoffrey E},
    journal={arXiv preprint arXiv:2004.13912},
    year={2020}
  }

Disclaimer about COMPAS dataset: It is important to note that developing a machine learning model to predict pre-trial detention has a number of important ethical considerations. You can learn more about these issues in the Partnership on AI Report on Algorithmic Risk Assessment Tools in the U.S. Criminal Justice System. The Partnership on AI is a multi-stakeholder organization -- of which Google is a member -- that creates guidelines around AI.

We’re using the COMPAS dataset only as an example of how to identify and remediate fairness concerns in data. This dataset is canonical in the algorithmic fairness literature.

Disclaimer: This is not an official Google product.

Release history Release notifications | RSS feed

This version

0.3

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for nam-pt, version 0.3
Filename, size File type Python version Upload date Hashes
Filename, size nam_pt-0.3-py3-none-any.whl (9.4 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size nam-pt-0.3.tar.gz (10.9 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page