Deterministic Uncertainty Estimation for Multi-Modal Regression With Deep Neural Networks

Prediction interval (PI) is a common method to represent predictive uncertainty in regression by deep neural networks. This paper proposes an extension of the prediction interval by using a union of disjoint intervals. Since previous PI methods assumed a single-interval PI (one lower and upper bound...

Full description

Saved in:
Bibliographic Details
Main Authors: Jaehak Cho, Jae Myung Kim, Seungyub Han, Jungwoo Lee
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10909531/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Prediction interval (PI) is a common method to represent predictive uncertainty in regression by deep neural networks. This paper proposes an extension of the prediction interval by using a union of disjoint intervals. Since previous PI methods assumed a single-interval PI (one lower and upper bound), it suffers from performance degradation in uncertainty estimation when the conditional density function is multi-modal. This paper demonstrates the need to include multi-modality in uncertainty estimation for regression. To address the issue, we propose a novel method that generates a union of disjoint PI&#x2019;s. With UCI benchmark experiments, the proposed method is shown to improve over current state-of-the-art uncertainty quantification methods, reducing an average PI width by over <inline-formula> <tex-math notation="LaTeX">$27~\%$ </tex-math></inline-formula>. With qualitative experiments, it is shown that multi-modality often exists in real-world datasets, and our method produces high-quality PI&#x2019;s compared to existing PI methods.
ISSN:2169-3536