https://github.com/nomnomnonono/fairdro
About Unofficial implementation of paper "Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization"
https://github.com/nomnomnonono/fairdro
deep-learning fairness fairness-ai fairness-ml machine-learning pytorch responsible-ai trustworthy-ai
Last synced: 6 months ago
JSON representation
About Unofficial implementation of paper "Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization"
- Host: GitHub
- URL: https://github.com/nomnomnonono/fairdro
- Owner: nomnomnonono
- Created: 2023-05-24T06:59:47.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-09-16T12:44:36.000Z (about 2 years ago)
- Last Synced: 2025-02-07T07:32:06.680Z (8 months ago)
- Topics: deep-learning, fairness, fairness-ai, fairness-ml, machine-learning, pytorch, responsible-ai, trustworthy-ai
- Language: Python
- Homepage:
- Size: 47.9 KB
- Stars: 3
- Watchers: 2
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# FairDRO: Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization
In progress...
非公式のFairDRO (https://openreview.net/forum?id=Q-WfHzmiG9m) の再現実装です．
## 実行環境
docker-composeを用います．インストールしていない人は公式のドキュメントに従ってインストールしてください．
- Dockerイメージの作成
```bash
$ make build
```
- Dockerコンテナ起動
```bash
$ make up
```
- Dockerコンテナに入る
```bash
$ make exec
```
## 実行例
```bash
$ python main.py --rho $rho --lr 0.001 --wd 0.001 -s $seed -b 256 -d celeba --target Smiling --sens Male --arch $model -e 50 --root data/CelebA/
```