无需标签即可动态调学习率，让模型自适应标签分布变化
ASAP: Unsupervised Post-training with Label Distribution Shift Adaptive Learning Rate
- 通过计算前后输出的余弦距离，动态调节学习率
- 在多个数据集上提升准确率，适应速度更快且更稳定
- 轻量级设计，仅需上一轮softmax输出，适合部署
在真实场景中，机器学习模型常面临在线标签分布漂移问题。有效适应需精细调整学习率：过低则适应缓慢，过高则引发不稳定。本文提出ASAP（Adaptive Shift Aware Post-training），通过计算当前与前一时刻无标签输出间的余弦距离，并将其映射至有界范围来动态调节学习率。ASAP无需标签、模型集成或历史输入，仅依赖上一轮softmax输出，实现快速轻量级适应。在多个数据集和漂移场景下的实验表明，ASAP持续提升准确率与效率，具备实际应用价值。
原文摘要 · Abstract (English)
In real-world applications, machine learning models face online label shift, where label distributions change over time. Effective adaptation requires careful learning rate selection: too low slows adaptation and too high causes instability. We propose ASAP (Adaptive Shift Aware Post-training), which dynamically adjusts the learning rate by computing the cosine distance between current and previous unlabeled outputs and mapping it within a bounded range. ASAP requires no labels, model ensembles, or past inputs, using only the previous softmax output for fast, lightweight adaptation. Experiments across multiple datasets and shift scenarios show ASAP consistently improves accuracy and efficiency, making it practical for unsupervised model adaptation.
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。