https://github.com/birkhoffg/rocoursenet

This is the official repository of the paper "RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model".
https://github.com/birkhoffg/rocoursenet

counterfactual-explanations explainable-ai explanation jax jax-relax recourse

Last synced: 13 days ago
JSON representation

This is the official repository of the paper "RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model".

• Host: GitHub
• URL: https://github.com/birkhoffg/rocoursenet
• Owner: BirkhoffG
• License: apache-2.0
• Created: 2023-01-20T00:01:52.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-10-22T20:51:06.000Z (about 1 year ago)
• Last Synced: 2023-10-22T21:28:49.299Z (about 1 year ago)
• Topics: counterfactual-explanations, explainable-ai, explanation, jax, jax-relax, recourse
• Language: Jupyter Notebook
• Homepage: https://arxiv.org/abs/2206.00700
• Size: 83.6 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model

[![Arxiv](https://img.shields.io/badge/Arxiv-2206.00700-orange)](https://arxiv.org/pdf/2206.00700.pdf)

[![DOI:10.1145/3583780.3615040](http://img.shields.io/badge/DOI-10.1145/3583780.3615040-B31B1B.svg)](https://dl.acm.org/doi/10.1145/3583780.3615040)

This repo contains code to reproduce our paper published at [CIKM 2023](https://arxiv.org/pdf/2206.00700.pdf).

To cite this paper:

```bibtex

@inproceedings{guo2023rocoursenet,

author = {Guo, Hangzhi and Jia, Feiran and Chen, Jinghui and Squicciarini, Anna and Yadav, Amulya},

title = {RoCourseNet: Robust Training of a Prediction Aware Recourse Model},

year = {2023},

isbn = {9798400701245},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

url = {https://doi.org/10.1145/3583780.3615040},

doi = {10.1145/3583780.3615040},

booktitle = {Proceedings of the 32nd ACM International Conference on Information and Knowledge Management},

pages = {619–628},

numpages = {10},

keywords = {explainable artificial intelligence, adversarial machine learning, counterfactual explanation, algorithmic recourse, interpretability},

location = {Birmingham, United Kingdom},

series = {CIKM '23}

}

```

## Install

This project uses 

[jax-relax](https://github.com/BirkhoffG/ReLax/tree/master) (a fast and scalable recourse explanation library).

Ths library is highly scalable and extensible, which enables our experiments to be finished within 30 minutes.

In contrast, a pytorch implementation of RoCourseNet takes around 12 hours to run.

```sh

pip install -e ".[dev]" --upgrade

```

## Run Experiments

Running `scripts.experiment.py` with different arguments will reproduce results in our paper. For example,

1. Train and Evaluate RoCourseNet on Loan Application Dataset:

```sh

python -m scripts.experiment.py -d loan

```

2. Train and Evaluate CounterNet on Loan Application Dataset:

```sh

python -m scripts.experiment.py -m CounterNet -d loan

```

3. Train and Evaluate ROAR on Loan Application Dataset:

```sh

python -m scripts.experiment.py -m ROAR -d loan

```