One-Shot Federated Conformal Prediction

Pierre Humbert, Batiste Le Bars, Aurélien Bellet, Sylvain Arlot
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:14153-14177, 2023.

Abstract

In this paper, we present a Conformal Prediction method that computes prediction sets in a one-shot Federated Learning (FL) setting. More specifically, we introduce a novel quantile-of-quantiles estimator and prove that for any distribution, it is possible to compute prediction sets with desired coverage in only one round of communication. To mitigate privacy issues, we also describe a locally differentially private version of our estimator. Finally, over a wide range of experiments, we show that our method returns prediction sets with coverage and length very similar to those obtained in a centralized setting. These results demonstrate that our method is well-suited for one-shot Federated Learning.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-humbert23a, title = {One-Shot Federated Conformal Prediction}, author = {Humbert, Pierre and Le Bars, Batiste and Bellet, Aur\'{e}lien and Arlot, Sylvain}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {14153--14177}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/humbert23a/humbert23a.pdf}, url = {https://proceedings.mlr.press/v202/humbert23a.html}, abstract = {In this paper, we present a Conformal Prediction method that computes prediction sets in a one-shot Federated Learning (FL) setting. More specifically, we introduce a novel quantile-of-quantiles estimator and prove that for any distribution, it is possible to compute prediction sets with desired coverage in only one round of communication. To mitigate privacy issues, we also describe a locally differentially private version of our estimator. Finally, over a wide range of experiments, we show that our method returns prediction sets with coverage and length very similar to those obtained in a centralized setting. These results demonstrate that our method is well-suited for one-shot Federated Learning.} }
Endnote
%0 Conference Paper %T One-Shot Federated Conformal Prediction %A Pierre Humbert %A Batiste Le Bars %A Aurélien Bellet %A Sylvain Arlot %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-humbert23a %I PMLR %P 14153--14177 %U https://proceedings.mlr.press/v202/humbert23a.html %V 202 %X In this paper, we present a Conformal Prediction method that computes prediction sets in a one-shot Federated Learning (FL) setting. More specifically, we introduce a novel quantile-of-quantiles estimator and prove that for any distribution, it is possible to compute prediction sets with desired coverage in only one round of communication. To mitigate privacy issues, we also describe a locally differentially private version of our estimator. Finally, over a wide range of experiments, we show that our method returns prediction sets with coverage and length very similar to those obtained in a centralized setting. These results demonstrate that our method is well-suited for one-shot Federated Learning.
APA
Humbert, P., Le Bars, B., Bellet, A. & Arlot, S.. (2023). One-Shot Federated Conformal Prediction. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:14153-14177 Available from https://proceedings.mlr.press/v202/humbert23a.html.

Related Material