为机器学习添加可解释的可靠性监控，提升系统稳定性与恢复能力。
Parent-Guided Adaptive Reliability (PGAR): A Behavioural Meta-Learning Framework for Stable and Trustworthy AI
- 引入家长层监督学习过程，动态调节学习速率以应对扰动。
- 在扰动下损失方差降低37%，恢复速度提升52%，校准性能更优。
- 适合作为安全关键场景中的可解释可靠性插件模块。
Parent-Guided Adaptive Reliability (PGAR) 是一种轻量级行为元学习框架，在标准学习器之上增加一个监督性“家长”层，以提升系统在扰动下的稳定性、校准性和恢复能力。PGAR计算三种反射级信号（事件检测、过度自信修正、恢复记忆），并融合为[0,1]区间内的有界可靠性指数。该指数持续调节学习器的有效学习率：不稳定时减小更新幅度，可靠性恢复后逐步恢复。我们提供了基于李雅普诺夫的证明框架，在损失平滑、下降方向和反射输出有界的温和假设下，证明了可靠性动态的有界适应性。在代表性学习任务上的实证评估显示，相比标准优化器，PGAR在保持计算简单的同时，提升了校准性能，降低了37%的损失方差，并实现52%更快的恢复速度。PGAR可作为即插即用的可靠性层集成于现有优化与学习流程中，支持安全相关场景中的可解释可靠性追踪。
原文摘要 · Abstract (English)
Parent-Guided Adaptive Reliability (PGAR) is a lightweight behavioural meta-learning framework that adds a supervisory "parent" layer on top of a standard learner to improve stability, calibration, and recovery under disturbances. PGAR computes three reflex-level signals (incident detection, overconfidence correction, and recovery memory) and fuses them into a bounded reliability index in [0,1]. This index continuously modulates the learner's effective learning rate, reducing update magnitude during instability and restoring it as reliability improves. We provide a Lyapunov-based proof sketch establishing bounded adaptation of the reliability dynamics under mild assumptions (smooth loss, descent direction, and bounded reflex outputs). Empirical evaluations on representative learning tasks show improved calibration, reduced loss variance, and faster recovery compared to standard optimizers, while retaining computational simplicity. PGAR functions as a plug-in reliability layer for existing optimization and learning pipelines, supporting interpretable reliability traces in safety-relevant settings.
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。