mlsanityData to 14 Oct 2026

Federated Conformal Predictors for Distributed Uncertainty Quantification

arXiv 2305.17564 ↗First posted 27 May 2023cs.LGcited by 46

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 46 papers in the map (data through 14 Oct 2026). Builds on 39 of its 64 references that are in the map. First posted on arXiv 27 May 2023.

Builds on

39 of 64 references.

References · 39

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2020Scaling Laws for Neural Language Modelscited by 6,586
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  4. 2017On Calibration of Modern Neural Networkscited by 4,960
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  6. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  7. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  8. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  9. 2018Federated Learning with Non-IID Datacited by 1,108
  10. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  11. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  12. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
27 more
  1. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  2. 2016Distribution-Free Predictive Inference For Regressioncited by 668
  3. 2020The Future of Digital Health with Federated Learningcited by 633
  4. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  5. 2019Agnostic Federated Learningcited by 456
  6. 2020Classification with Valid and Adaptive Coveragecited by 396
  7. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 366
  8. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  9. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 305
  10. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 288
  11. 2016Least Ambiguous Set-Valued Classifiers with Bounded Error Levelscited by 272
  12. 2021Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Controlcited by 271
  13. 2021Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Datasetcited by 185
  14. 2022Revisiting Neural Scaling Laws in Language and Visioncited by 132
  15. 2020Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertaintycited by 129
  16. 2022FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settingscited by 125
  17. 2022Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imagingcited by 107
  18. 2021Fair Conformal Predictors for Applications in Medical Imagingcited by 74
  19. 2021Few-shot Conformal Prediction with Auxiliary Taskscited by 53
  20. 2022Robust Calibration with Multi-domain Temperature Scalingcited by 39
  21. 2022Improving Trustworthiness of AI Disease Severity Rating in Medical Imaging with Ordinal Conformal Prediction Setscited by 38
  22. 2022On the Utility of Prediction Sets in Human-AI Teamscited by 34
  23. 2022TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernelscited by 26
  24. 2022Semantic uncertainty intervals for disentangled latent spacescited by 22
  25. 2021Distribution-Free Federated Learning with Conformal Predictionscited by 16
  26. 2019DDSketch: A fast and fully-mergeable quantile sketch with relative-error guaranteescited by 8
  27. 2022Three Applications of Conformal Prediction for Rating Breast Density in Mammographycited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 15; 2025: 10; 2026: 18.

46 papers.

Sort:

By area:

  1. 2024Benchmarking LLMs via Uncertainty Quantificationcited by 126
  2. 2023Conformal Prediction for Deep Classifier via Label Rankingcited by 53
  3. 2024Conformal Prediction: A Data Perspectivecited by 25
  4. 2025Wasserstein-regularized Conformal Prediction under General Distribution Shiftcited by 15
  5. 2024On Temperature Scaling and Conformal Prediction of Deep Classifierscited by 13
  6. 2024Does confidence calibration improve conformal prediction?cited by 12
  7. 2024Multi-Source Conformal Inference Under Distribution Shiftcited by 11
  8. 2023Federated Inference with Reliable Uncertainty Quantification over Wireless Channels via Conformal Predictioncited by 10
  9. 2023Efficient Conformal Prediction under Data Heterogeneitycited by 9
  10. 2024Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimationcited by 9
  11. 2024Certifiably Byzantine-Robust Federated Conformal Predictioncited by 8
  12. 2024Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasetscited by 7
34 more
  1. 2024What If We Had Used a Different App? Reliable Counterfactual KPI Analysis in Wireless Systemscited by 6
  2. 2024Uncertainty quantification in metric spacescited by 4
  3. 2025Distributed Conformal Prediction via Message Passingcited by 4
  4. 2026Efficient Federated Conformal Prediction with Group-Conditional Guaranteecited by 4
  5. 2024Marginal and training-conditional guarantees in one-shot federated conformal predictioncited by 3
  6. 2025Don't Reach for the Stars: Rethinking Topology for Resilient Federated Learningcited by 3
  7. 2025FedCF: Fair Federated Conformal Predictioncited by 3
  8. 2024Future-Proofing Medical Imaging with Privacy-Preserving Federated Learning and Uncertainty Quantification: A Reviewcited by 2
  9. 2025Conformal Prediction Adaptive to Unknown Subpopulation Shiftscited by 2
  10. 2025Conformal and kNN Predictive Uncertainty Quantification Algorithms in Metric Spacescited by 2
  11. 2025Federated Conditional Conformal Prediction via Generative Modelscited by 2
  12. 2026Multi-Distribution Robust Conformal Predictioncited by 2
  13. 2026Conformalized Neural Networks for Federated Uncertainty Quantification under Dual Heterogeneitycited by 2
  14. 2026Certified Adaptive Refresh: Anytime-Valid Monitoring for Federated Conformal RAGcited by 2
  15. 2024TPFL: A Trustworthy Personalized Federated Learning Framework via Subjective Logiccited by 1
  16. 2025Segmentation-Guided CT Synthesis with Pixel-Wise Conformal Uncertainty Boundscited by 1
  17. 2026Partial Model Sharing Improves Byzantine Resilience in Federated Conformal Predictioncited by 1
  18. 2026Online Conformal Prediction: Enforcing monotonicity via Online Optimizationcited by 1
  19. 2026Multi-Agent Conformal Prediction with Personalized Statistical Validitycited by 1
  20. 2024Distribution-Free Fair Federated Learning with Small Samplescited by 0
  21. 2024Conformal Prediction for Federated Graph Neural Networks with Missing Neighbor Informationcited by 0
  22. 2025DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differencescited by 0
  23. 2025Cost-Sensitive Conformal Training with Provably Controllable Learning Boundscited by 0
  24. 2026Communication-Efficient Byzantine-Robust Federated Conformal Prediction via Partial Sharingcited by 0
  25. 2026Softmax is not Enough (for Adaptive Conformal Classification)cited by 0
  26. 2026TrustFed: Enabling Trustworthy Medical AI under Data Privacy Constraintscited by 0
  27. 2026Continual Calibration: Coverage Can Collapse Before Accuracy in Lifelong LLM Fine-Tuningcited by 0
  28. 2026Robust Conditional Conformal Prediction via Branched Normalizing Flowcited by 0
  29. 2026FedeKD: Energy-Based Gating for Robust Federated Knowledge Distillation under Heterogeneous Settingscited by 0
  30. 2026When Average Calibration Fails: Site-Conditional Federated Conformal Risk Controlcited by 0
  31. 2026Private Anytime Selective-Risk Certification for Federated Retrieval-Augmented Generation: Guarantees and Empirical Limitscited by 0
  32. 2026Beyond Parameter Space: NTK-Guided Personalized Aggregation for Robust Federated Learningcited by 0
  33. 2026A Unified Perspective on Conformal Prediction and Wasserstein Distributionally Robust Optimization for Uncertainty Quantificationcited by 0
  34. 2026Multi-source conformal prediction: leveraging heterogeneity via localizationcited by 0