mlsanityData to 7 Oct 2026

Random-Set Neural Networks (RS-NN)

arXiv 2307.05772 ↗First posted 11 Jul 2023cs.LG stat.MLcited by 19

Not on the map. Why?

Abstract (arXiv)

Machine learning is increasingly deployed in safety-critical domains where erroneous predictions may lead to potentially catastrophic consequences, highlighting the need for learning systems to be aware of how confident they are in their own predictions: in other words, 'to know when they do not know'. In this paper, we propose a novel Random-Set Neural Network (RS-NN) approach to classification which predicts belief functions (rather than classical probability vectors) over the class list using the mathematics of random sets, i.e., distributions over the collection of sets of classes. RS-NN encodes the 'epistemic' uncertainty induced by training sets that are insufficiently representative or limited in size via the size of the convex set of probability vectors associated with a predicted belief function. Our approach outperforms state-of-the-art Bayesian and Ensemble methods in terms of accuracy, uncertainty estimation and out-of-distribution (OoD) detection on multiple benchmarks (CIFAR-10 vs SVHN/Intel-Image, MNIST vs FMNIST/KMNIST, ImageNet vs ImageNet-O). RS-NN also scales up effectively to large-scale architectures (e.g. WideResNet-28-10, VGG16, Inception V3, EfficientNetB2 and ViT-Base-16), exhibits remarkable robustness to adversarial attacks and can provide statistical guarantees in a conformal learning setting.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 57 of its 151 references that are in the map. First posted on arXiv 11 Jul 2023.

Builds on

57 of 151 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  7. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  8. 2016Wide Residual Networkscited by 3,057
  9. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  11. 2019Natural Adversarial Examplescited by 1,401
  12. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
38 more
  1. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  2. 2017Selective Classification for Deep Neural Networkscited by 799
  3. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  4. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  5. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  6. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  7. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  8. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  9. 2018Deep Learning for Classical Japanese Literaturecited by 415
  10. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  11. 2021Revisiting the Calibration of Modern Neural Networkscited by 387
  12. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  13. 2020Hands-on Bayesian Neural Networks -- a Tutorial for Deep Learning Userscited by 336
  14. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  15. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 163
  16. 2015Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inferencecited by 159
  17. 2019Ensemble Distribution Distillationcited by 158
  18. 2020Uncertainty Quantification and Deep Ensemblescited by 138
  19. 2019Functional Variational Bayesian Neural Networkscited by 127
  20. 2021Epistemic Neural Networkscited by 120
  21. 2017Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimizationcited by 113
  22. 2019Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustnesscited by 104
  23. 2022Semantic Probabilistic Layers for Neuro-Symbolic Learningcited by 103
  24. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  25. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  26. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  27. 2022Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisationcited by 65
  28. 2022Deep Ensembles Work, But Are They Necessary?cited by 63
  29. 2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
  30. 2020All You Need is a Good Functional Prior for Bayesian Deep Learningcited by 61
  31. 2017Imposing Hard Constraints on Deep Networks: Promises and Limitationscited by 42
  32. 2023Is the Volume of a Credal Set a Good Measure for Epistemic Uncertainty?cited by 40
  33. 2018Uncertainty in the Variational Information Bottleneckcited by 39
  34. 2020Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?cited by 39
  35. 2022ROAD-R: The Autonomous Driving Dataset with Logical Requirementscited by 34
  36. 2020Fast Predictive Uncertainty for Classification with Bayesian Deep Networkscited by 31
  37. 2021An evidential classifier based on Dempster-Shafer theory and deep learningcited by 18
  38. 2020A Simple Framework for Uncertainty in Contrastive Learningcited by 16

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 6; 2026: 11.

19 papers.

Sort:

By area:

  1. 2025Integral Imprecise Probability Metricscited by 11
  2. 2025A Unified Evaluation Framework for Epistemic Predictionscited by 10
  3. 2025Epistemic Artificial Intelligence is Essential for Machine Learning Models to Truly 'Know When They Do Not Know'cited by 8
  4. 2025Random-Set Large Language Modelscited by 7
  5. 2023Reasoning with random sets: An agenda for the futurecited by 6
  6. 2026Learning Credal Ensembles via Distributionally Robust Optimizationcited by 6
  7. 2024Generalising realisability in statistical learning theory under epistemic uncertaintycited by 5
  8. 2025Epistemic Wrapping for Uncertainty Quantificationcited by 5
  9. 2025Uncertainty-Aware Autonomous Vehicles: Predicting the Road Aheadcited by 5
  10. 2026Epistemic Generative Adversarial Networkscited by 4
  11. 2026Random-Set Graph Neural Networkscited by 3
  12. 2026Credal Large Language Models for Semantic Commitment under Uncertaintycited by 2
7 more
  1. 2026Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Studycited by 1
  2. 2026A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classificationcited by 1
  3. 2026A formal definition and meta-model for a machine theory of mindcited by 1
  4. 2026What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamicscited by 1
  5. 2026Decision-Aligned Evaluation of Uncertainty Quantificationcited by 1
  6. 2026Possibilistic Predictive Uncertainty for Deep Learningcited by 0
  7. 2026XU-RS: Explaining Credal Width in Random-Set Language Modelscited by 0