Generalized Evidential Deep Learning: From a Bayesian Perspective
2026-05-25 • Machine Learning
Machine LearningComputer Vision and Pattern Recognition
AI summaryⓘ
The authors studied a method called Evidential Deep Learning (EDL), which helps machines know how uncertain they are without needing extra guesswork. They found that past versions of EDL didn't have a clear theory behind them, so they created a new, unified framework named Generalized Evidential Deep Learning (GEDL). This new approach explains how uncertainty is measured from a Bayesian perspective and links different versions of EDL together. Their experiments show GEDL works well for tasks like classification and detecting unusual data, while being based on solid theory.
Evidential Deep LearningUncertainty EstimationBayesian FrameworkPosterior UpdatePrior SpecificationAsymptotic AnalysisOut-of-Distribution DetectionClassificationGeneralized Evidential Deep Learning
Authors
Yuanye Liu, Yibo Gao, Yuanyang Chen, Xiahai Zhuang
Abstract
Evidential Deep Learning (EDL) has emerged as an efficient, sampling-free strategy for uncertainty estimation. A series of EDL variants have been proposed to address specific limitations of the original framework, achieving notable success. However, the underlying theoretical structure of EDL and the relationships among these variants have received limited systematic investigation. In this work, we establish a principled theoretical foundation for EDL by interpreting it within a generalized Bayesian framework that includes prior specification, posterior update, and training objective. We further characterize evidential uncertainty from a Bayesian distributional uncertainty viewpoint, established via asymptotic analysis. Building on this perspective, we further propose Generalized Evidential Deep Learning (GEDL), a unified and extensible framework that explicitly disentangles the roles of individual components and systematically relates GEDL to existing variants. Extensive experiments demonstrate that GEDL yields comparable results on classification, uncertainty estimation and OOD detections, with theoretical grounding.