无需训练即可准确分类时间序列，性能媲美最强方法。
RocketPFN: Accurate Time Series Classification via In-Context Learning
- 用随机卷积提取特征，再用预训练模型做上下文分类。
- 在92个UCR数据集上平均准确率达0.900，推理仅需30秒/折。
- 无参数、少特征，适合快速评估零样本时间序列模型。
我们提出RocketPFN，一种无需训练的时间序列分类管道，结合随机卷积特征提取（Rocket）与预训练表格基础模型（TabPFN v2.5）的上下文分类能力。在92个UCR数据集（30次重采样协议）上，其平均准确率与当前最强方法HC2持平（均为0.900，Wilcoxon p=0.50），且每折中位推理时间仅30秒。它还显著优于HC2集成中的任一单分类器。在UEA数据集（20个）上，差异亦不显著。与时间序列基础模型对比：当搭配相同下游分类器MOMENT时，MOMENT、Mantis及MantisV2均被RocketPFN显著超越（每项p<0.001），且使用更少特征、无学习参数，即使这些编码器曾基于包含UCR训练样本的语料库预训练过。我们建议该两阶段流程作为评估零样本时间序列基础模型的基准。
原文摘要 · Abstract (English)
We introduce RocketPFN, a training-free pipeline for time series classification that combines random convolutional feature extraction (Rocket) with in-context classification via a pretrained tabular foundation model (TabPFN v2.5). On 92 UCR datasets (30-resample protocol), RocketPFN matches HC2, the strongest published method on the archive, in mean accuracy (both 0.900, Wilcoxon p=0.50), with no training on the target data and a median inference time of 30 seconds per fold. It also significantly outperforms every individual classifier in the HC2 ensemble. On UEA (20 datasets) the difference is likewise not statistically significant. A separate comparison concerns TSC foundation models: when paired with the same downstream classifier, MOMENT, Mantis, and MantisV2 are all significantly outperformed by RocketPFN using fewer extracted features and no learned parameters (p<0.001 in each case). This holds even when the encoders were pretrained on corpora that include the UCR training samples. We propose this two-stage pipeline as a reference point for evaluating zero-shot TSC foundation models.
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。