Data

Tools

Indexes

Applications

Experiments

Open Source Science

nifr

Null-sampling for Interpretable and Fair Representations

https://github.com/wearepal/nifr

Science Score: 54.0%

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

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.6%) to scientific vocabulary

Keywords

domain-adaptation eccv-2020 fairness invertible-neural-networks pytorch
Last synced: 6 months ago · JSON representation ·

Repository

Null-sampling for Interpretable and Fair Representations

Basic Info
  • Host: GitHub
  • Owner: wearepal
  • License: gpl-3.0
  • Language: Jupyter Notebook
  • Default Branch: master
  • Homepage:
  • Size: 23.1 MB
Statistics
  • Stars: 9
  • Watchers: 1
  • Forks: 0
  • Open Issues: 5
  • Releases: 0
Topics
domain-adaptation eccv-2020 fairness invertible-neural-networks pytorch
Created about 7 years ago · Last pushed about 3 years ago
Metadata Files
Readme License Citation

README.md

Conference arXiv

Null-sampling for Interpretable and Fair Representations

Implementation of our paper Null-sampling for Interpretable and Fair Representations.

Requirements

Python 3.8 (or higher)

Installing dependencies

The dependencies are listed in the setup.py. To install them all, do

pip install -e .

Running the code

Training of the CelebA cFlow model can be reproduced for CelebA and cMNIST, respectively, with the folowing commands

python start_inn.py --dataset celeba --levels 3 --level-depth 32 --glow True --reshape-method squeeze --autoencode False --input-noise True --quant-level 5 --use-wandb True --factor-splits 0=0.5 1=0.5 --train-on-recon False --recon-detach False --batch-size 32 --nll-weight 1 --pred-s-weight 1e-2 --zs-frac 0.001 --coupling-channels 512 --super-val True --super-val-freq 10 --val-freq 1 --task-mixing 0.5 --gpu 0 --num-discs 10 --disc-channels 512 --data-split-seed 42 --iters 76000

python start_inn.py --dataset cmnist --levels 3 --level-depth 24 --glow True --reshape-method squeeze --autoencode False --input-noise True --quant-level 5 --use-wandb True --factor-splits 0=0.5 1=0.5 --train-on-recon False --recon-detach False --batch-size 256 --test-batch-size 512 --nll-weight 1 --pred-s-weight 1e-2 --zs-frac 0.002 --coupling-channels 512 --super-val True --super-val-freq 5 --val-freq 1 --task-mixing 0 --gpu 0 --num-discs 1 --disc-channels 512 --level-depth 24 --num-discs 3

Citing This Work

bibtex @InProceedings{KehBarThoQua20, author = {Kehrenberg, Thomas and Bartlett, Myles and Thomas, Oliver and Quadrianto, Novi}, editor = {Vedaldi, Andrea and Bischof, Horst and Brox, Thomas and Frahm, Jan-Michael}, title = {Null-Sampling for Interpretable and Fair Representations}, booktitle = {Computer Vision -- ECCV 2020}, year = {2020}, publisher = {Springer International Publishing}, address = {Cham}, pages = {565--580}, isbn = {978-3-030-58574-7} }

Owner

  • Name: Predictive Analytics Lab
  • Login: wearepal
  • Kind: organization
  • Location: University of Sussex, Brighton, UK

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
title: "Null-sampling for Interpretable and Fair Representations"
authors:
- family-names: "Kehrenberg"
  given-names: "Thomas"
  orcid: "https://orcid.org/0000-0002-2347-7165"
- family-names: "Bartlett"
  given-names: "Myles"
- family-names: "Thomas"
  given-names: "Oliver"
  orcid: "https://orcid.org/0000-0001-8162-9633"
version: 1.0.0  
date-released: 2020-08-01
url: "https://github.com/predictive-analytics-lab/nifr"
preferred-citation:
  type: "conference-paper"
  authors:
  - family-names: "Kehrenberg"
    given-names: "Thomas"
    orcid: "https://orcid.org/0000-0002-2347-7165"
  - family-names: "Bartlett"
    given-names: "Myles"
  - family-names: "Thomas"
    given-names: "Oliver"
    orcid: "https://orcid.org/0000-0001-8162-9633"
  - family-names: "Quadrianto"
    given-names: "Novi"
  title: "Null-sampling for Interpretable and Fair Representations"
  doi: "10.1007/978-3-030-58574-7_34"
  url: "https://github.com/predictive-analytics-lab/nifr"
  isbn: "978-3-030-58574-7"
  editors: 
  - family-names: "Vedaldi"
    given-names: "Andrea"
  - family-names: "Bischof"
    given-names: "Horst"
  - family-names: "Brox"
    given-names: "Thomas"
  - family-names: "Frahm"
    given-names: "Jan-Michael"
  collection-title: "Computer Vision -- ECCV 2020"
  collection-type: "conference"
  year: 2020
  publisher: 
  - name: "Springer International Publishing"
    address: "Cham"
  pages: "565--580"

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 7
  • Total pull requests: 144
  • Average time to close issues: 4 months
  • Average time to close pull requests: about 1 month
  • Total issue authors: 3
  • Total pull request authors: 3
  • Average comments per issue: 1.14
  • Average comments per pull request: 0.17
  • Merged pull requests: 114
  • 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
View more stats
Top Authors
Issue Authors
  • olliethomas (4)
  • CVAnonymous (1)
  • scutfrank (1)
Pull Request Authors
  • tmke8 (45)
  • MylesBartlett (33)
  • olliethomas (16)
Top Labels
Issue Labels
Pull Request Labels