X-PLAIN is an interactive tool that allows human-in-the-loop inspection of the decision-making process of machine learning models.
- Read the full paper.
- Watch the demonstration video.
Bring Your Own Data to X-PLAIN. Pastor, Eliana, and Elena Baralis. Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data. 2020.
# Create a virtualenv folder
mkdir -p ~/venv-environments/x-plain
# Create a new virtualenv in that folder
python3 -m venv ~/venv-environments/x-plain
# Activate the virtualenv
source ~/venv-environments/x-plain/bin/activate
# Install deps
pip install flask numpy pandas scipy snapshottest scikit-learn matplotlib seaborn
pip install --no-binary orange3 orange3==3.15.0FLASK_ENV=development flask runcd demo_frontend/my-app
npm install # Only needed on the first run
npm startVisit localhost:3000 in a browser.
Eliana Pastor, Elena Baralis and Andrea Congolato (interface design).
@inproceedings{pastor2020xplain,
author = {Pastor, Eliana and Baralis, Elena},
title = {Bring Your Own Data to X-PLAIN},
year = {2020},
isbn = {9781450367356},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3318464.3384710},
doi = {10.1145/3318464.3384710},
booktitle = {Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data},
pages = {2805–2808},
numpages = {4},
keywords = {interpretability, prediction explanation, local rules},
location = {Portland, OR, USA},
series = {SIGMOD ’20}
}