# Conformalized Neural Networks for Federated Uncertainty Quantification under Dual Heterogeneity

arXiv: https://arxiv.org/abs/2602.23296 · HTML: https://mlsanity.com/paper/2602.23296/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 11 of 11)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Conformalized Quantile Regression](https://mlsanity.com/paper/1905.03222/) (2019)
- [Classification with Valid and Adaptive Coverage](https://mlsanity.com/paper/2006.02544/) (2020)
- [Fair Federated Medical Image Segmentation via Client Contribution Estimation](https://mlsanity.com/paper/2303.16520/) (2023)
- [Federated Conformal Predictors for Distributed Uncertainty Quantification](https://mlsanity.com/paper/2305.17564/) (2023)
- [Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentation](https://mlsanity.com/paper/2203.10144/) (2022)
- [Conformal Prediction for Federated Uncertainty Quantification Under Label Shift](https://mlsanity.com/paper/2306.05131/) (2023)
- [One-Shot Federated Conformal Prediction](https://mlsanity.com/paper/2302.06322/) (2023)
- [Efficient Conformal Prediction under Data Heterogeneity](https://mlsanity.com/paper/2312.15799/) (2023)
- [Asymmetrical Reciprocity-based Federated Learning for Resolving Disparities in Medical Diagnosis](https://mlsanity.com/paper/2412.19654/) (2024)

## Built on by (most cited first, 2 of 2)

- [FedeKD: Energy-Based Gating for Robust Federated Knowledge Distillation under Heterogeneous Settings](https://mlsanity.com/paper/2605.05553/) (2026)
- [When Average Calibration Fails: Site-Conditional Federated Conformal Risk Control](https://mlsanity.com/paper/2606.20115/) (2026)

## Abstract (arXiv)

Federated learning (FL) faces challenges in uncertainty quantification (UQ). Without reliable UQ, FL systems risk deploying overconfident models at under-resourced agents, leading to silent local failures despite seemingly satisfactory global performance. Existing federated UQ approaches often address data heterogeneity or model heterogeneity in isolation, overlooking their joint effect on coverage reliability across agents. Conformal prediction is a widely used distribution-free UQ framework, yet its applications in heterogeneous FL settings remains underexplored. We provide FedWQ-CP, a simple yet effective approach that balances empirical coverage performance with efficiency at both global and agent levels under the dual heterogeneity. FedWQ-CP performs agent-server calibration in a single communication round. On each agent, conformity scores are computed on calibration data and a local quantile threshold is derived. Each agent then transmits only its quantile threshold and calibration sample size to the server. The server simply aggregates these thresholds through a weighted average to produce a global threshold. Experimental results on seven public datasets for both classification and regression demonstrate that FedWQ-CP empirically maintains agent-wise and global coverage while producing the smallest prediction sets or intervals.