This repository contains code for our ICML 2022 paper Active Sampling for Min-Max Fairness.
In order to reproduce the experiments of our paper, do the following:
-
install all required packages as specified in
environment.yml
-
run one of the scripts
experiment_drug_consumption_dataset.py
,experiment_drug_consumption_dataset_tradeoff_curve.py
,experiment_COMPAS_dataset.py
, orexperiment_diabetes_dataset.py
(when running a script, the required dataset will be downloaded automatically --- make sure you are connected to the internet)
If you publish material that uses this code, please cite our paper:
@inproceedings{abernethy2022ActiveSampling,
title={Active Sampling for Min-Max Fairness},
author={Abernethy, Jacob and Awasthi, Pranjal and Kleindessner, Matthäus and Morgenstern, Jamie and Russell, Chris and Zhang, Jie},
year={2022},
booktitle={International Conference on Machine Learning (ICML)}
}
See CONTRIBUTING for more information.
This project is licensed under the Apache-2.0 License.