Uncertainty Estimation by Fisher Information-based Evidential Deep Learning

by   Danruo Deng, et al.

Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. Recently proposed evidential neural networks explicitly account for different uncertainties by treating the network's outputs as evidence to parameterize the Dirichlet distribution, and achieve impressive performance in uncertainty estimation. However, for high data uncertainty samples but annotated with the one-hot label, the evidence-learning process for those mislabeled classes is over-penalized and remains hindered. To address this problem, we propose a novel method, Fisher Information-based Evidential Deep Learning (ℐ-EDL). In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes. The generalization ability of our network is further improved by optimizing the PAC-Bayesian bound. As demonstrated empirically, our proposed method consistently outperforms traditional EDL-related algorithms in multiple uncertainty estimation tasks, especially in the more challenging few-shot classification settings.


page 1

page 2

page 3

page 4


Information Robust Dirichlet Networks for Predictive Uncertainty Estimation

Precise estimation of uncertainty in predictions for AI systems is a cri...

Towards Maximizing the Representation Gap between In-Domain & Out-of-Distribution Examples

Among existing uncertainty estimation approaches, Dirichlet Prior Networ...

Multidimensional Uncertainty-Aware Evidential Neural Networks

Traditional deep neural networks (NNs) have significantly contributed to...

Understanding VAEs in Fisher-Shannon Plane

In information theory, Fisher information and Shannon information (entro...

Uncertainty-Aware Reliable Text Classification

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

On the Variance of the Fisher Information for Deep Learning

The Fisher information matrix (FIM) has been applied to the realm of dee...

Probabilistic orientation estimation with matrix Fisher distributions

This paper focuses on estimating probability distributions over the set ...

Please sign up or login with your details

Forgot password? Click here to reset