TS-ACL：面向时间序列的持续学习的闭式解
TS-ACL: Closed-Form Solution for Time Series-oriented Continual Learning
AI总结：
针对时间序列类增量学习的灾难性遗忘与类内变异问题，提出TS-ACL，通过无梯度闭式解避免遗忘并学习全局分布处理变异，在五个基准数据集上性能接近联合训练，优于现有方法，建立新SOTA。
摘要：
时间序列分类支撑着医疗诊断、多媒体场景中手势驱动交互系统等关键应用。然而，时间序列类增量学习（TSCIL）面临两大挑战：灾难性遗忘和类内变异。灾难性遗忘的产生是因为基于梯度的参数更新策略不可避免地擦除过往知识。与图像不同，时间序列数据呈现出特定主体模式，即类内变异，指同一类别内观察到的模式差异。基于范例的方法因样本有限无法覆盖多样变异，现有无范例方法则缺乏处理类内变异的显式机制。为解决这两大挑战，我们提出TS-ACL，其利用无梯度闭式解避免基于梯度优化方法固有的灾难性遗忘问题，同时学习全局分布以解决类内变异。在覆盖多种传感器模态和任务的五个基准数据集上的大量实验表明，TS-ACL在四个数据集上的性能接近联合训练，优于现有方法并为TSCIL建立了新的最先进（SOTA）水平。
英文摘要：
Time series classification underpins critical applications such as healthcare diagnostics and gesture-driven interactive systems in multimedia scenarios. However, time series class-incremental learning (TSCIL) faces two major challenges: catastrophic forgetting and intra-class variations. Catastrophic forgetting occurs because gradient-based parameter update strategies inevitably erase past knowledge. And unlike images, time series data exhibits subject-specific patterns, also known as intra-class variations, which refer to differences in patterns observed within the same class. While exemplar-based methods fail to cover diverse variation with limited samples, existing exemplar-free methods lack explicit mechanisms to handle intra-class variations. To address these two challenges, we propose TS-ACL, which leverages a gradient-free closed-form solution to avoid the catastrophic forgetting problem inherent in gradient-based optimization methods while simultaneously learning global distributions to resolve intra-class variations. Additionally, it provides privacy protection and efficiency. Extensive experiments on five benchmark datasets covering various sensor modalities and tasks demonstrate that TS-ACL achieves performance close to joint training on four datasets, outperforming existing methods and establishing a new state-of-the-art (SOTA) for TSCIL.
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。
