Conformalized Neural Networks for Federated Uncertainty Quantification under Dual Heterogeneity

Quang-Huy Nguyen, Jiaqi Wang, Wei-Shinn Ku|February 26, 2026arXiv

Key Takeaway

Federated learning systems can now quantify prediction uncertainty reliably across heterogeneous devices with minimal communication overhead using ...

Summary

This paper solves a critical problem in federated learning: how to know when your model is uncertain about its predictions, especially when different devices have different types of data.

training safety efficiency

Key Terms

federated-learning uncertainty-quantification conformal-prediction data-heterogeneity