mlsanityData to 14 Oct 2026

Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation

arXiv 2110.03051 ↗First posted 6 Oct 2021cs.LG cs.AI stat.MLcited by 71

Not on the map. Why?

Abstract (arXiv)

Popular approaches for quantifying predictive uncertainty in deep neural networks often involve distributions over weights or multiple models, for instance via Markov Chain sampling, ensembling, or Monte Carlo dropout. These techniques usually incur overhead by having to train multiple model instances or do not produce very diverse predictions. This comprehensive and extensive survey aims to familiarize the reader with an alternative class of models based on the concept of Evidential Deep Learning: For unfamiliar data, they aim to admit "what they don't know", and fall back onto a prior belief. Furthermore, they allow uncertainty estimation in a single model and forward pass by parameterizing distributions over distributions. This survey recapitulates existing works, focusing on the implementation in a classification setting, before surveying the application of the same paradigm to regression. We also reflect on the strengths and weaknesses compared to other existing methods and provide the most fundamental derivations using a unified notation to aid future research.

Key facts. Cited by 71 papers in the map (data through 14 Oct 2026). Builds on 92 of its 192 references that are in the map. First posted on arXiv 6 Oct 2021.

Builds on

92 of 192 references.

References · 92

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017On Calibration of Modern Neural Networkscited by 4,960
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  6. 2013Auto-Encoding Variational Bayescited by 4,053
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  8. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  11. 2015Variational Inference with Normalizing Flowscited by 2,170
  12. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
38 more
  1. 2016Adversarial examples in the physical worldcited by 1,769
  2. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  3. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  4. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  5. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
  6. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  7. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  8. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  9. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  10. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  11. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 792
  12. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  13. 2015Image-based Recommendations on Styles and Substitutescited by 706
  14. 2018Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNscited by 588
  15. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  16. 2015Weight Uncertainty in Neural Networkscited by 554
  17. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  18. 2019Measuring Calibration in Deep Learningcited by 446
  19. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  20. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 443
  21. 2018Deep Learning for Classical Japanese Literaturecited by 422
  22. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  23. 2021Revisiting the Calibration of Modern Neural Networkscited by 390
  24. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  25. 2018Snips Voice Platform: an embedded Spoken Language Understanding system for private-by-design voice interfacescited by 377
  26. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 371
  27. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 365
  28. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 364
  29. 2019Deep Evidential Regressioncited by 355
  30. 2017Snapshot Ensembles: Train 1, get M for freecited by 350
  31. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  32. 2020Calibration of Pre-trained Transformerscited by 315
  33. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 308
  34. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  35. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  36. 2020Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networkscited by 231
  37. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  38. 2020Efficient and Scalable Bayesian Neural Nets with Rank-1 Factorscited by 171

50 most cited of 92 All 92 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 12; 2024: 19; 2025: 24; 2026: 16.

71 papers.

Sort:

By area:

  1. 2023Second-Order Uncertainty Quantification: A Distance-Based Approachcited by 35
  2. 2024Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?cited by 35
  3. 2023Think Twice Before Selection: Federated Evidential Active Learning for Medical Image Analysis with Domain Shiftscited by 28
  4. 2025Estimating LLM Uncertainty with Evidencecited by 26
  5. 2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
  6. 2024Label-wise Aleatoric and Epistemic Uncertainty Quantificationcited by 22
  7. 2024Uncertainty Estimation by Density Aware Evidential Deep Learningcited by 22
  8. 2023EVORA: Deep Evidential Traversability Learning for Risk-Aware Off-Road Autonomycited by 21
  9. 2023Random-Set Neural Networks (RS-NN)cited by 19
  10. 2023Second-Order Uncertainty Quantification: Variance-Based Measurescited by 19
  11. 2024Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?cited by 18
  12. 2024Credal Wrapper of Model Averaging for Uncertainty Estimation in Classificationcited by 13
38 more
  1. 2023Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applicationscited by 11
  2. 2024Hyper Evidential Deep Learning to Quantify Composite Classification Uncertaintycited by 11
  3. 2025Is GPT-OSS Good? A Comprehensive Evaluation of OpenAI's Latest Open Source Modelscited by 11
  4. 2025Uncertainty Estimation by Flexible Evidential Deep Learningcited by 10
  5. 2025Position: Epistemic uncertainty estimation methods are fundamentally incompletecited by 9
  6. 2024PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terraincited by 8
  7. 2025Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'cited by 8
  8. 2025Credal and Interval Deep Evidential Classificationscited by 8
  9. 2025A calibration test for evaluating set-based epistemic uncertainty representationscited by 7
  10. 2023Computing a human-like reaction time metric from stable recurrent vision modelscited by 6
  11. 2023Conformalizing Machine Translation Evaluationcited by 5
  12. 2023Deep Evidential Learning for Bayesian Quantile Regressioncited by 5
  13. 2023Improvements on Uncertainty Quantification for Node Classification via Distance-Based Regularizationcited by 5
  14. 2024Uncertainty Estimation for 3D Object Detection via Evidential Learningcited by 5
  15. 2024Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusioncited by 5
  16. 2025Reducing Aleatoric and Epistemic Uncertainty through Multi-modal Data Acquisitioncited by 5
  17. 2024Weakly-Supervised Residual Evidential Learning for Multi-Instance Uncertainty Estimationcited by 4
  18. 2024Wasserstein Gradient Boosting: A Framework for Distribution-Valued Supervised Learningcited by 4
  19. 2023How Does Traffic Environment Quantitatively Affect the Autonomous Driving Prediction?cited by 3
  20. 2024Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learningcited by 3
  21. 2024GRAM: Generalization in Deep RL with a Robust Adaptation Modulecited by 3
  22. 2025Label Calibration in Source Free Domain Adaptationcited by 3
  23. 2025Improving Group Robustness on Spurious Correlation via Evidential Alignmentcited by 3
  24. 2025Flow Stochastic Segmentation Networkscited by 3
  25. 2025Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detectioncited by 3
  26. 2026Uncertainty in Physics and AI: Taxonomy, Quantification, and Validationcited by 3
  27. 2026ELVAE: Evidential Learning-Based Variational Autoencoder for Uncertainty-Aware Generationcited by 3
  28. 2024Uncertainty-aware Semantic Mapping in Off-road Environments with Dempster-Shafer Theory of Evidencecited by 2
  29. 2024Adaptive Label Smoothing for Out-of-Distribution Detectioncited by 2
  30. 2024DeepUQ: Assessing the Aleatoric Uncertainties from two Deep Learning Methodscited by 2
  31. 2025Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimizationcited by 2
  32. 2025SurvUnc: A Meta-Model Based Uncertainty Quantification Framework for Survival Analysiscited by 2
  33. 2025Anomalies by Synthesis: Anomaly Detection using Generative Diffusion Models for Off-Road Navigationcited by 2
  34. 2025Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AIcited by 2
  35. 2025Towards Trustworthy Vital Sign Forecasting: Leveraging Uncertainty for Prediction Intervalscited by 2
  36. 2025Generalized Zero-Shot Learning for Point Cloud Segmentation with Evidence-Based Dynamic Calibrationcited by 2
  37. 2026Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrievalcited by 2
  38. 2023Human-in-the-loop: Towards Label Embeddings for Measuring Classification Difficultycited by 1

50 most cited of 71 All 71 (JSON)