Federated Conformal Predictors for Distributed Uncertainty Quantification
This work addresses uncertainty quantification in distributed and heterogeneous environments, which is an incremental advancement for federated learning applications.
The authors tackled the challenge of applying conformal prediction to federated learning by proposing a weaker notion of partial exchangeability to handle data heterogeneity, resulting in the Federated Conformal Prediction (FCP) framework with rigorous theoretical guarantees and excellent empirical performance on computer vision and medical imaging datasets.
Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning since it can be easily applied as a post-processing step to already trained models. In this paper, we extend conformal prediction to the federated learning setting. The main challenge we face is data heterogeneity across the clients - this violates the fundamental tenet of exchangeability required for conformal prediction. We propose a weaker notion of partial exchangeability, better suited to the FL setting, and use it to develop the Federated Conformal Prediction (FCP) framework. We show FCP enjoys rigorous theoretical guarantees and excellent empirical performance on several computer vision and medical imaging datasets. Our results demonstrate a practical approach to incorporating meaningful uncertainty quantification in distributed and heterogeneous environments. We provide code used in our experiments https://github.com/clu5/federated-conformal.