Residual bayesian attention networks for uncertainty quantification in regression tasks

用于回归任务中不确定性量化的残差贝叶斯注意力网络

阅读:2

Abstract

The demand for uncertainty quantification in modern sequence modeling tasks has prompted researchers to explore deep integration between Bayesian inference and Transformer architectures, but existing methods still face systematic engineering challenges in key technical aspects such as attention mechanism probabilization, residual connection uncertainty propagation, and epistemic-aleatoric uncertainty decoupling. This study proposes the Residual Bayesian Attention (RBA) framework, which achieves end-to-end probabilistic inference capabilities through three tightly coupled core components: Bayesian feedforward layers establish differentiable propagation mechanisms for parameter-level uncertainty, multi-layer residual Bayesian attention embeds radial basis function kernels into attention computation and introduces adaptive residual weights modeled by Beta distributions, and the Bayesian covariance construction module generates mathematically rigorous covariance representations through outer product operations and eigenvalue correction. Systematic evaluation on benchmark datasets covering six domains including engineering optimization, time series forecasting, and spatial modeling demonstrates that RBA achieves stable uncertainty quantification performance in medium-scale structured data scenarios, particularly exhibiting technical advantages in prediction interval calibration quality. Notably, through objective evaluation of challenging tasks such as complex physical systems, this study identifies the common technical boundaries of current deep learning methods in multi-physics coupled system modeling, providing important empirical insights for the development direction of this field. Therefore, RBA, as a systematic engineering integration framework of Bayesian inference and Transformer architecture, provides a methodological contribution with clearly defined applicability boundaries for principled uncertainty quantification in deep sequence modeling.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。