cs.LG提交于 2026-10-28已译

评估贝叶斯深度学习在分布偏移下的鲁棒生物医学时间序列分类：睡眠评分案例研究

Evaluating Bayesian deep learning for robust biomedical time-series classification under distribution shift: A sleep scoring case study

Mads Birch S{\o}rensen · Ulrike Richter · Francois Gastambide · Michael Riis Andersen

中文摘要

生物医学时间序列分类中，机器学习模型常因分布偏移导致精度与校准性能下降。本研究探讨贝叶斯模型平均（BMA）如何提升鲁棒性，以啮齿动物睡眠评分为案例，评估基因型、实验室及物种分布偏移下的BMA表现。系统比较了两种神经网络骨干网络在分布内（ID）及五个分布外（OOD）数据集上，涵盖单盆地与多盆地的九种近似推断方法。结果显示，多盆地方法表现最佳，优于基线及单盆地方法。与点估计相比，BMA在两种架构下普遍提升了OOD精度与校准，ID增益较小。此外，BMA通常改善了选择性预测及OOD与伪影检测，但未改善评分者间分歧检测。

关键要点

01针对生物医学时间序列分类中分布偏移导致的精度与校准下降问题，研究贝叶斯模型平均的鲁棒性。
02以啮齿动物睡眠评分为案例，在基因型、实验室和物种偏移场景下，系统比较九种近似推断方法。
03多盆地方法表现最佳，优于基线及单盆地方法，在两种网络架构上均优于点估计。
04BMA普遍提升分布外精度与校准，改善选择性预测及伪影检测，但未改善评分者间分歧检测。

解读

尚无解读。

原始英文摘要

arXiv:2610.35484v1 Announce Type: new Abstract: In biomedical time-series classification, machine learning models often suffer from deteriorating accuracy and calibration due to distribution shift. We investigate to what degree Bayesian-inspired deep learning improves robustness through Bayesian model averaging (BMA). Using rodent sleep scoring as a case study, we evaluate BMA under distribution shifts in genotype, laboratory, and species. We systematically compare nine approximate inference methods spanning single- and multi-basin approaches across two neural network backbones on in-distribution (ID) data and five out-of-distribution (OOD) datasets. In our results, multi-basin methods perform best, outperforming baselines and single-basin methods. Compared with point estimates, BMA generally improves OOD accuracy and calibration across both architectures, while yielding only modest ID gains. It also often improves selective prediction and OOD and artifact detection, but, interestingly, not inter-rater disagreement detection.