AI 中文总结
本文提出学习时代（AoL）度量预测误差的时间持续性，用于离线与流式训练，在长尾分类中提升或匹配基线，补充传统难度信号。
AI 中文摘要
当前机器学习算法主要依赖瞬时信号（如损失、边际和预测置信度）来刻画模型行为。这些信号指示了当前优化步骤中预测的难度，但并未捕捉模型保持错误状态的时间长度。我们研究学习的这一时间维度，并引入学习时代（Age of Learning, AoL），一种衡量预测误差随时间持续性的学习状态变量。AoL在错误未解决时增加，并在获得正确预测时重置，从而区分持续欠学习与瞬时错误。我们开发了基于AoL的训练策略，适用于离线与流式设置。在离线学习中，样本级AoL在训练过程中累积，并聚合成类级状态，以指导自适应重加权和重采样。在流式学习中，由于无法访问完整历史数据，我们利用当前和缓冲的观测维护轻量级类级AoL状态。在长尾分类设置中，AoL改善或匹配标准训练基线，当学习难度随时间持续时收益更大。多种子流式实验进一步显示，在时间稳定的不平衡下，AoL带来可复现的增益。对类别频率、损失和边际的分析表明，AoL与常规难度度量相关，但捕获了关于错误持续时间的额外信息。这些结果表明，时间持续性为刻画和控制不平衡及非平稳环境中的学习动态提供了有用的补充信号。
英文摘要
Current machine learning algorithms primarily rely on instantaneous signals such as loss, margin, and prediction confidence to characterize model behavior. These signals indicate how difficult a prediction is at the current optimization step, but they do not capture how long the model has remained incorrect. We study this temporal dimension of learning and introduce Age of Learning (AoL), a learning-state variable that measures the persistence of prediction errors over time. AoL increases while an error remains unresolved and resets when a correct prediction is achieved, thereby distinguishing persistent under-learning from transient mistakes. We develop AoL-based training strategies for both offline and streaming settings. In offline learning, sample-level AoL is accumulated over training and aggregated into class-level states that guide adaptive reweighting and resampling. In streaming learning, where full historical access is unavailable, we maintain lightweight class-level AoL states using current and buffered observations. Across long-tailed classification settings, AoL improves or matches standard training baselines, with larger benefits when learning difficulty persists over time. Multi-seed streaming experiments further show reproducible gains under temporally stable imbalance. Analysis of class frequency, loss, and margin shows that AoL is related to conventional difficulty measures but captures additional information about error duration. These results suggest that temporal persistence provides a useful complementary signal for characterizing and controlling learning dynamics in imbalanced and non-stationary environments.
