Multidimensional Uncertainty-Aware Evidential Neural Networks

by   Yibo Hu, et al.

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.


page 2

page 5


Quantifying Classification Uncertainty using Regularized Evidential Neural Networks

Traditional deep neural nets (NNs) have shown the state-of-the-art perfo...

Uncertainty-Aware Reliable Text Classification

Deep neural networks have significantly contributed to the success in pr...

Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance

In real-world scenarios, typical visual recognition systems could fail u...

Learning Structural Weight Uncertainty for Sequential Decision-Making

Learning probability distributions on the weights of neural networks (NN...

Uncertainty Estimation by Fisher Information-based Evidential Deep Learning

Uncertainty estimation is a key factor that makes deep learning reliable...

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection

Misclassification detection is an important problem in machine learning,...

Evidential Deep Learning to Quantify Classification Uncertainty

Deterministic neural nets have been shown to learn effective predictors ...

Please sign up or login with your details

Forgot password? Click here to reset