从贝叶斯视角统一了不确定性学习框架，让模型更可信。
Generalized Evidential Deep Learning: From a Bayesian Perspective
- 用广义贝叶斯理论重新解释证据深度学习
- 提出统一框架GEDL，理论与实验均表现稳定
- 适合关注模型可信度与泛化能力的研究者
证据深度学习（EDL）作为一种高效且无需采样的不确定性估计方法已受到广泛关注。尽管已有多个变体被提出以解决原框架的局限性并取得显著成效，但其内在理论结构及各变体间的关联仍缺乏系统研究。本文从广义贝叶斯框架出发，构建了包含先验设定、后验更新和训练目标的严谨理论基础，并通过渐近分析从分布不确定性角度刻画证据不确定性。在此基础上，我们提出通用证据深度学习（GEDL），一个统一且可扩展的框架，明确解耦各组件角色，系统关联现有变体。大量实验证明，GEDL在分类、不确定性估计和分布外检测任务上表现相当，具备坚实的理论支撑。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。