mlsanityData to 14 Oct 2026

FedCal: Achieving Local and Global Calibration in Federated Learning via Aggregated Parameterized Scaler

arXiv 2405.15458 ↗First posted 24 May 2024cs.LG cs.DCcited by 6

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) enables collaborative machine learning across distributed data owners, but data heterogeneity poses a challenge for model calibration. While prior work focused on improving accuracy for non-iid data, calibration remains under-explored. This study reveals existing FL aggregation approaches lead to sub-optimal calibration, and theoretical analysis shows despite constraining variance in clients' label distributions, global calibration error is still asymptotically lower bounded. To address this, we propose a novel Federated Calibration (FedCal) approach, emphasizing both local and global calibration. It leverages client-specific scalers for local calibration to effectively correct output misalignment without sacrificing prediction accuracy. These scalers are then aggregated via weight averaging to generate a global scaler, minimizing the global calibration error. Extensive experiments demonstrate FedCal significantly outperforms the best-performing baseline, reducing global calibration error by 47.66% on average.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 44 of its 66 references that are in the map. First posted on arXiv 24 May 2024.

Builds on

44 of 66 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  5. 2019Advances and Open Problems in Federated Learningcited by 3,046
  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. 2018Federated Learning with Non-IID Datacited by 1,108
  9. 2020Adaptive Federated Optimizationcited by 1,046
  10. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  11. 2020The Future of Digital Health with Federated Learningcited by 633
  12. 2019Federated Learning with Personalization Layerscited by 541
32 more
  1. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
  2. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  3. 2022Git Re-Basin: Merging Models modulo Permutation Symmetriescited by 471
  4. 2021Towards Personalized Federated Learningcited by 464
  5. 2019Bayesian Nonparametric Federated Learning of Neural Networkscited by 387
  6. 2020Adaptive Personalized Federated Learningcited by 358
  7. 2019Verified Uncertainty Calibrationcited by 309
  8. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 305
  9. 2019The Non-IID Data Quagmire of Decentralized Machine Learningcited by 305
  10. 2021The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networkscited by 291
  11. 2021Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Controlcited by 271
  12. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  13. 2017Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryptioncited by 176
  14. 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 166
  15. 2021Federated Learning for Open Bankingcited by 141
  16. 2015Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networkscited by 139
  17. 2020Uncertainty Quantification and Deep Ensemblescited by 139
  18. 2022Federated Learning with Label Distribution Skew via Logits Calibrationcited by 109
  19. 2021Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibrationcited by 79
  20. 2021Personalized Federated Learning with Gaussian Processescited by 76
  21. 2020SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimatescited by 75
  22. 2019Calibration of Encoder Decoder Models for Neural Machine Translationcited by 68
  23. 2020Intra Order-preserving Functions for Calibration of Multi-Class Neural Networkscited by 65
  24. 2022Deep Ensembles Work, But Are They Necessary?cited by 63
  25. 2019Practical Federated Gradient Boosting Decision Treescited by 54
  26. 2021Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learningcited by 52
  27. 2022Federated Graph Neural Networks: Overview, Techniques and Challengescited by 52
  28. 2022Robust Calibration with Multi-domain Temperature Scalingcited by 39
  29. 2019Real-World Image Datasets for Federated Learningcited by 30
  30. 2023Conformal Prediction for Federated Uncertainty Quantification Under Label Shiftcited by 29
  31. 2021Distribution-Free Federated Learning with Conformal Predictionscited by 16
  32. 2021When Are Solutions Connected in Deep Networks?cited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 3; 2026: 1.

6 papers.

  1. 2024Unlocking the Potential of Model Calibration in Federated Learningcited by 3
  2. 2025AFCL: Analytic Federated Continual Learning for Spatio-Temporal Invariance of Non-IID Datacited by 3
  3. 2024Future-Proofing Medical Imaging with Privacy-Preserving Federated Learning and Uncertainty Quantification: A Reviewcited by 2
  4. 2025Private Federated Multiclass Post-hoc Calibrationcited by 0
  5. 2025How (Mis)calibrated is your Federated CLIP and what to do about it?cited by 0
  6. 2026Temperature Scaling Attack Disrupting Model Confidence in Federated Learningcited by 0