deepee

Differentially Private Deep Learning in PyTorch

https://github.com/gkaissis/deepee

Science Score: 20.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org
  • Committers with academic emails
    1 of 4 committers (25.0%) from academic institutions
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (4.7%) to scientific vocabulary

Keywords from Contributors

transformation
Last synced: 11 months ago · JSON representation

Repository

Differentially Private Deep Learning in PyTorch

Basic Info
  • Host: GitHub
  • Owner: gkaissis
  • License: apache-2.0
  • Language: Python
  • Default Branch: master
  • Homepage: http://g-k.ai/deepee/
  • Size: 938 KB
Statistics
  • Stars: 29
  • Watchers: 2
  • Forks: 7
  • Open Issues: 4
  • Releases: 0
Archived
Created over 5 years ago · Last pushed almost 5 years ago
Metadata Files
Readme License

README.md

deepee

deepee is a library for differentially private deep learning in PyTorch. More precisely, deepee implements the Differentially Private Stochastic Gradient Descent (DP-SGD) algorithm originally described by Abadi et al.. Despite the name, deepee works with any (first order) optimizer, including Adam, AdaGrad, etc.

It wraps a regular PyTorch model and takes care of calculating per-sample gradients, clipping, noising and accumulating gradients with an API which closely mimics the PyTorch API of the original model.

Check out the documentation here

For paper readers

If you would like to reproduce the results from our paper, please go here

Owner

  • Name: Georgios Kaissis
  • Login: gkaissis
  • Kind: user
  • Company: TUM, Imperial College, OpenMined

GitHub Events

Total
  • Watch event: 2
  • Fork event: 2
Last Year
  • Watch event: 2
  • Fork event: 2

Committers

Last synced: almost 3 years ago

All Time
  • Total Commits: 80
  • Total Committers: 4
  • Avg Commits per committer: 20.0
  • Development Distribution Score (DDS): 0.513
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Georgios Kaissis 39
Georgios Kaissis 4****s 24
Alex Ziller a****r@t****e 16
Nicolas Remerscheid N****e 1
Committer Domains (Top 20 + Academic)
tum.de: 1

Issues and Pull Requests

Last synced: 12 months ago

All Time
  • Total issues: 5
  • Total pull requests: 5
  • Average time to close issues: about 17 hours
  • Average time to close pull requests: 7 days
  • Total issue authors: 4
  • Total pull request authors: 3
  • Average comments per issue: 0.4
  • Average comments per pull request: 0.2
  • Merged pull requests: 5
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
  • a1302z (2)
  • canoztas (1)
  • ghost (1)
  • gkaissis (1)
Pull Request Authors
  • a1302z (3)
  • NiWaRe (1)
  • dimasquest (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 65 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 1
  • Total versions: 9
  • Total maintainers: 1
pypi.org: deepee

Fast (and cheeky) differentially private gradient-based optimisation in PyTorch

  • Versions: 9
  • Dependent Packages: 0
  • Dependent Repositories: 1
  • Downloads: 65 Last month
Rankings
Dependent packages count: 10.0%
Stargazers count: 12.3%
Forks count: 13.3%
Average: 19.8%
Dependent repos count: 21.7%
Downloads: 41.9%
Maintainers (1)
Last synced: 12 months ago

Dependencies

environment.yml pypi
  • testfixtures *
pyproject.toml pypi
  • python >=3.7