Conformal Prediction for Federated Uncertainty Quantification Under Label Shift
Abstract
Federated Learning (FL) is a machine learning framework where many clients collaboratively train models while keeping the training data decentralized. Despite recent advances in FL, the uncertainty quantification topic (UQ) remains partially addressed. Among UQ methods, conformal prediction (CP) approaches provides distribution-free guarantees under minimal assumptions. We develop a new federated conformal prediction method based on quantile regression and take into account privacy constraints. This method takes advantage of importance weighting to effectively address the label shift between agents and provides theoretical guarantees for both valid coverage of the prediction sets and differential privacy. Extensive experimental studies demonstrate that this method outperforms current competitors.
Cite
Text
Plassier et al. "Conformal Prediction for Federated Uncertainty Quantification Under Label Shift." International Conference on Machine Learning, 2023.Markdown
[Plassier et al. "Conformal Prediction for Federated Uncertainty Quantification Under Label Shift." International Conference on Machine Learning, 2023.](https://mlanthology.org/icml/2023/plassier2023icml-conformal/)BibTeX
@inproceedings{plassier2023icml-conformal,
title = {{Conformal Prediction for Federated Uncertainty Quantification Under Label Shift}},
author = {Plassier, Vincent and Makni, Mehdi and Rubashevskii, Aleksandr and Moulines, Eric and Panov, Maxim},
booktitle = {International Conference on Machine Learning},
year = {2023},
pages = {27907-27947},
volume = {202},
url = {https://mlanthology.org/icml/2023/plassier2023icml-conformal/}
}