FETERS：基于有效比率选择的少样本早期时间序列分类
FETERS: Few-Shot Early Time-Series Classification via Effective Ratio Selection
AI总结：
本文提出FETERS少样本早期时间序列分类框架，通过类留一法选停止比率、惩罚奖励函数平衡权衡，结合Rocket特征与Chronos表示，在69个数据集的5样本设置下达最优性能。
AI中文摘要：
早期时间序列分类（ETSC）旨在从部分观测的时间序列中尽早做出准确预测。尽管已开发出多种停止机制和特征学习策略用于ETSC，但大多数现有方法假设可获取充足的带标注训练数据，这在标注有限的应用场景中可能不切实际。在监督有限的情况下，学习额外的样本级停止模块和提取有效分类特征都会变得具有挑战性。本文提出FETERS，一种少样本ETSC框架，它通过在支持集上进行按类留一法（LOO）评估来选择数据集级的停止比率，并使用基于惩罚的奖励函数来平衡准确率与早停的权衡，从而避免了训练额外停止模块的需求。FETERS进一步将基于Rocket的特征与冻结的Chronos表示相结合用于分类。在涵盖14个领域的69个公共数据集上进行的大量实验表明，FETERS在5样本（5-shot）设置下实现了当前最优（SOTA）性能，具有最高的平均调和均值（HM），并在38个数据集上取得最佳HM，同时在44个数据集上优于当前最优方法。FETERS在全样本（full-shot）设置下也保持竞争力，证明了其在平衡准确率与早停权衡方面的有效性。
英文摘要：
Early time-series classification (ETSC) aims to make accurate predictions from partially observed time series as early as possible. Although various stopping mechanisms and feature learning strategies have been developed for ETSC, most existing methods assume access to sufficient labeled training data, which may be unrealistic in applications with limited annotation. Under limited supervision, learning an additional sample-level stopping module and extracting effective classification features can both become challenging. In this paper, we propose FETERS, a few-shot ETSC framework that selects a dataset-level stopping ratio through class-wise leave-one-out (LOO) evaluation on the support set and uses a penalty-based reward function to manage the accuracy-earliness trade-off, thereby avoiding the need to train an additional stopping module. FETERS further combines Rocket-based features with frozen Chronos representations for classification. Extensive experiments on 69 public datasets spanning 14 domains show that FETERS achieves state-of-the-art (SOTA) performance in the 5-shot setting, with the highest average harmonic mean (HM) and the best HM on 38 datasets, while outperforming the current SOTA method on 44 datasets. FETERS also remains competitive in the full-shot setting, demonstrating its effectiveness in managing the accuracy-earliness trade-off.
