# Multidimensional Uncertainty-Aware Evidential Neural Networks

arXiv: https://arxiv.org/abs/2012.13676 · HTML: https://mlsanity.com/paper/2012.13676/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Dec 2020.

## Built on by (most cited first, 16 of 16)

- [Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation](https://mlsanity.com/paper/2110.03051/) (2021)
- [A Comprehensive Survey on Evidential Deep Learning and Its Applications](https://mlsanity.com/paper/2409.04720/) (2024)
- [Uncertainty-Aware Reliable Text Classification](https://mlsanity.com/paper/2107.07114/) (2021)
- [Uncertainty Estimation by Density Aware Evidential Deep Learning](https://mlsanity.com/paper/2409.08754/) (2024)
- [Revisiting Essential and Nonessential Settings of Evidential Deep Learning](https://mlsanity.com/paper/2410.00393/) (2024)
- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [Continual Evidential Deep Learning for Out-of-Distribution Detection](https://mlsanity.com/paper/2309.02995/) (2023)
- [A Survey on Uncertainty Reasoning and Quantification for Decision Making: Belief Theory Meets Deep Learning](https://mlsanity.com/paper/2206.05675/) (2022)
- [SEED: Sound Event Early Detection via Evidential Uncertainty](https://mlsanity.com/paper/2202.02441/) (2022)
- [Efficient dataset construction using active learning and uncertainty-aware neural networks for plasma turbulent transport surrogate models](https://mlsanity.com/paper/2507.15976/) (2025)
- [Bi-level Meta-Policy Control for Dynamic Uncertainty Calibration in Evidential Deep Learning](https://mlsanity.com/paper/2510.08938/) (2025)
- [Similarity-as-Evidence: Calibrating Overconfident VLMs for Interpretable and Label-Efficient Medical Active Learning](https://mlsanity.com/paper/2602.18867/) (2026)
- [Scene Uncertainty and the Wellington Posterior of Deterministic Image Classifiers](https://mlsanity.com/paper/2106.13870/) (2021)
- [When Surface Form Changes Moderation Decisions: A Paired Study of Code-Mixed Workflow Instability](https://mlsanity.com/paper/2606.05654/) (2026)
- [Visualizing Uncertainty: Spatial Maps of Missing and Conflicting Evidence in Deep Learning](https://mlsanity.com/paper/2606.15767/) (2026)
- [Subtype Robustness Is Not Just Accuracy: Calibration Under Unseen Subtype Shift](https://mlsanity.com/paper/2608.00928/) (2026)

## Abstract (arXiv)

Traditional deep neural networks (NNs) have significantly contributed to the state-of-the-art performance in the task of classification under various application domains. However, NNs have not considered inherent uncertainty in data associated with the class probabilities where misclassification under uncertainty may easily introduce high risk in decision making in real-world contexts (e.g., misclassification of objects in roads leads to serious accidents). Unlike Bayesian NN that indirectly infer uncertainty through weight uncertainties, evidential NNs (ENNs) have been recently proposed to explicitly model the uncertainty of class probabilities and use them for classification tasks. An ENN offers the formulation of the predictions of NNs as subjective opinions and learns the function by collecting an amount of evidence that can form the subjective opinions by a deterministic NN from data. However, the ENN is trained as a black box without explicitly considering inherent uncertainty in data with their different root causes, such as vacuity (i.e., uncertainty due to a lack of evidence) or dissonance (i.e., uncertainty due to conflicting evidence). By considering the multidimensional uncertainty, we proposed a novel uncertainty-aware evidential NN called WGAN-ENN (WENN) for solving an out-of-distribution (OOD) detection problem. We took a hybrid approach that combines Wasserstein Generative Adversarial Network (WGAN) with ENNs to jointly train a model with prior knowledge of a certain class, which has high vacuity for OOD samples. Via extensive empirical experiments based on both synthetic and real-world datasets, we demonstrated that the estimation of uncertainty by WENN can significantly help distinguish OOD samples from boundary samples. WENN outperformed in OOD detection when compared with other competitive counterparts.