Personalized Federated Conformal Prediction with Localization
Yinjie Min, Chuchen Zhang, Liuhua Peng, Changliang Zou
Abstract
Personalized federated learning addresses data heterogeneity across distributed agents but lacks uncertainty quantification that is both agent-specific and instance-specific, which is a critical requirement for risk-sensitive applications. We propose personalized federated conformal prediction (PFCP), a novel framework that combines personalized federated learning with conformal prediction to provide statistically valid agent-personalized prediction sets with instance-localization. By leveraging privacy-preserving knowledge transfer from other source agents, PFCP ensures marginal coverage guarantees for target agents while significantly improving conditional coverage performance on individual test instances, which has been validated by extensive experiments.
BibTeX
@inproceedings{
min2025personalized,
title={Personalized Federated Conformal Prediction with Localization},
author={Yinjie Min and Chuchen Zhang and Liuhua Peng and Changliang Zou},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=QQUhGPST45}
}