AIR：用于持续学习的解析不平衡修正器
AIR: Analytic Imbalance Rectifier for Continual Learning
AI总结：
针对持续学习中的类别不平衡问题，提出解析不平衡修正器（AIR），通过解析重加权模块均衡类别权重，在长尾和Si-Blurry设置下显著提升准确率和宏F1分数。
摘要：
持续学习（CL）智能体从顺序到达的数据中增量学习，并适应现实世界环境的动态、不断变化的特性。然而，许多现有的持续学习方法在演化且不平衡的数据流中性能下降，原因是它们对类别频率变化的适应能力有限，或者未能有效利用来自新类别和先前观察类别的混合数据。为应对这些挑战，我们提出了一种用于现实世界持续学习的解析不平衡修正器（AIR）算法。AIR是一种在线无样本方法，采用冻结主干网络作为特征提取器，并使用闭式增量分类器，其权重等于针对相同类别加权岭目标函数的联合学习权重。AIR通过解析重加权模块（ARM）解决类别不平衡问题，该模块为损失函数中的每个类别计算一个重加权因子，以均衡各类别的总样本权重。在长尾类别增量学习下，AIR在总体准确率上领先28个基线方法，在总体宏F1分数上领先无样本方法，相比最强的无样本基线分别提升了3.21%的准确率和2.14%的宏F1分数。在具有重复类别的Si-Blurry设置下，AIR领先15个基于样本和无样本的基线方法，相比最强基线提升了2.32%的总体准确率和1.27%的总体宏F1分数。单侧配对检验支持这四项比较中的正平均绝对增益（Holm校正后p<0.006）。
英文摘要：
Continual learning (CL) agents incrementally learn from sequentially arriving data and adapt to the dynamic, ever-changing nature of real-world environments. However, many existing CL methods suffer performance degradation in evolving, imbalanced data streams due to limited adaptation to changing class frequencies or ineffective use of mixed data from new and previously observed classes. To deal with these challenges, we propose an analytic imbalance rectifier (AIR) algorithm for real-world CL. AIR is an online exemplar-free approach with a frozen backbone as the feature extractor and a closed-form incremental classifier whose weight equals the joint-learning weight for the same class-weighted ridge objective. AIR addresses class imbalance with an analytic reweighting module (ARM) that calculates a reweighting factor for each class in the loss function to equalize total sample weights across classes. Under long-tailed class-incremental learning, AIR leads 28 baselines in aggregate accuracy and exemplar-free methods in aggregate macro F1, gaining 3.21% accuracy and 2.14% macro F1 over the respective strongest exemplar-free baselines. Under the Si-Blurry setting with recurring classes, AIR leads 15 exemplar-based and exemplar-free baselines, gaining 2.32% aggregate accuracy and 1.27% aggregate macro F1 over the strongest baseline. One-sided paired tests support positive mean absolute gains in these four comparisons (Holm-adjusted p<0.006).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
