Quantifying Classification Uncertainty using Regularized Evidential Neural Networks
This work addresses the need for better uncertainty quantification in classification tasks, which is crucial for minimizing misclassification risks in real-life applications, but it appears incremental as it builds on existing evidential neural networks.
The paper tackles the problem of classification uncertainty in neural networks by proposing a regularized evidential neural network that explicitly models different types of inherent data uncertainty, such as vacuity and dissonance, and demonstrates improved learning of uncertainty modeling in experiments with synthetic and real-world datasets.
Traditional deep neural nets (NNs) have shown the state-of-the-art performance in the task of classification in various applications. However, NNs have not considered any types of uncertainty associated with the class probabilities to minimize risk due to misclassification under uncertainty in real life. Unlike Bayesian neural nets indirectly infering uncertainty through weight uncertainties, evidential neural networks (ENNs) have been recently proposed to support explicit modeling of the uncertainty of class probabilities. It treats predictions of an NN as subjective opinions and learns the function by collecting the evidence leading to these opinions by a deterministic NN from data. However, an ENN is trained as a black box without explicitly considering different types of inherent data uncertainty, such as vacuity (uncertainty due to a lack of evidence) or dissonance (uncertainty due to conflicting evidence). This paper presents a new approach, called a {\em regularized ENN}, that learns an ENN based on regularizations related to different characteristics of inherent data uncertainty. Via the experiments with both synthetic and real-world datasets, we demonstrate that the proposed regularized ENN can better learn of an ENN modeling different types of uncertainty in the class probabilities for classification tasks.