mlsanityData to 7 Oct 2026

Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks

arXiv 2312.11230 ↗First posted 18 Dec 2023stat.ML cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

In modern federated learning, one of the main challenges is to account for inherent heterogeneity and the diverse nature of data distributions for different clients. This problem is often addressed by introducing personalization of the models towards the data distribution of the particular client. However, a personalized model might be unreliable when applied to the data that is not typical for this client. Eventually, it may perform worse for these data than the non-personalized global model trained in a federated way on the data from all the clients. This paper presents a new approach to federated learning that allows selecting a model from global and personalized ones that would perform better for a particular input point. It is achieved through a careful modeling of predictive uncertainties that helps to detect local and global in- and out-of-distribution data and use this information to select the model that is confident in a prediction. The comprehensive experimental evaluation on the popular real-world image datasets shows the superior performance of the model in the presence of out-of-distribution data while performing on par with state-of-the-art personalized federated learning algorithms in the standard scenarios.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 32 of its 45 references that are in the map. First posted on arXiv 18 Dec 2023.

Builds on

32 of 45 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2015Variational Inference with Normalizing Flowscited by 2,161
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  9. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  10. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  11. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  12. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 682
20 more
  1. 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 565
  2. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  3. 2021Exploiting Shared Representations for Personalized Federated Learningcited by 537
  4. 2019Federated Learning with Personalization Layerscited by 533
  5. 2020Adaptive Personalized Federated Learningcited by 353
  6. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 322
  7. 2020Federated Learning of a Mixture of Global and Local Modelscited by 208
  8. 2020MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysiscited by 206
  9. 2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 180
  10. 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
  11. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 163
  12. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  13. 2021Towards Unbiased and Accurate Deferral to Multiple Expertscited by 71
  14. 2022Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisationcited by 65
  15. 2022On Uncertainty, Tempering, and Data Augmentation in Bayesian Classificationcited by 46
  16. 2023On Second-Order Scoring Rules for Epistemic Uncertainty Quantificationcited by 38
  17. 2022FedPop: A Bayesian Approach for Personalised Federated Learningcited by 35
  18. 2019Uncertainty on Asynchronous Time Event Predictioncited by 27
  19. 2023FedHB: Hierarchical Bayesian Federated Learningcited by 8
  20. 2023Training, Architecture, and Prior for Deterministic Uncertainty Methodscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 2; 2026: 2.

8 papers.

  1. 2024Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?cited by 34
  2. 2024From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimationcited by 27
  3. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 11
  4. 2026ReDAct: Uncertainty-Aware Deferral for LLM Agentscited by 5
  5. 2024Linear Opinion Pooling for Uncertainty Quantification on Graphscited by 2
  6. 2025Multidimensional Uncertainty Quantification via Optimal Transportcited by 1
  7. 2024CUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networkscited by 0
  8. 2026Different Corruptions, Different Signals: Uncertainty and Loss in Federated Data Qualitycited by 0