English

Efficient Conformal Prediction under Data Heterogeneity

Machine Learning 2024-07-16 v2 Machine Learning

Abstract

Conformal Prediction (CP) stands out as a robust framework for uncertainty quantification, which is crucial for ensuring the reliability of predictions. However, common CP methods heavily rely on data exchangeability, a condition often violated in practice. Existing approaches for tackling non-exchangeability lead to methods that are not computable beyond the simplest examples. This work introduces a new efficient approach to CP that produces provably valid confidence sets for fairly general non-exchangeable data distributions. We illustrate the general theory with applications to the challenging setting of federated learning under data heterogeneity between agents. Our method allows constructing provably valid personalized prediction sets for agents in a fully federated way. The effectiveness of the proposed method is demonstrated in a series of experiments on real-world datasets.

Keywords

Cite

@article{arxiv.2312.15799,
  title  = {Efficient Conformal Prediction under Data Heterogeneity},
  author = {Vincent Plassier and Nikita Kotelevskii and Aleksandr Rubashevskii and Fedor Noskov and Maksim Velikanov and Alexander Fishkov and Samuel Horvath and Martin Takac and Eric Moulines and Maxim Panov},
  journal= {arXiv preprint arXiv:2312.15799},
  year   = {2024}
}

Comments

29 pages

R2 v1 2026-06-28T14:01:41.568Z