arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.12147cs.LG
收藏

是时候了:迈向下一代时间序列预测基准

It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks

University of Science and Technology of China(中国科学技术大学);Tsinghua University(清华大学)

Zhongzheng Qiao, Sheng Pan, Anni Wang, Viktoriya Zhukova, Yong Liu, Xudong Jiang, Qingsong Wen, Mingsheng Long, Ming Jin, Chenghao Liu

AI总结:

针对现有时间序列基准在数据组成、完整性、任务设计和分析视角上的局限,提出TIME基准,包含50个新数据集和98个预测任务,采用人机协作管道确保数据完整性,并引入模式级评估视角,对12个基础模型进行多粒度排名。

摘要:

时间序列基础模型正在从特定数据集建模向通用任务评估转变,彻底改变预测格局。然而,我们认为现有基准在四个维度存在常见局限:受重复使用传统资源主导的受限数据组成、缺乏严格质量保证的数据完整性受损、脱离现实背景的任务公式错位,以及掩盖通用洞察的僵化分析视角。为弥补这些差距,我们引入TIME,一个下一代以任务为中心的基准,包含50个新数据集和98个预测任务,专为无数据泄露的严格零样本TSFM评估而设计。集成大语言模型和人类专业知识,我们建立了人机协同的基准构建管道以确保高数据完整性,并通过将预测配置与现实操作需求和变量可预测性对齐来重新定义任务公式。此外,我们提出一种新颖的模式级评估视角,超越了基于静态元标签的传统数据集级评估。通过利用结构时间序列特征来刻画内在时间属性,该方法提供了跨不同模式的模型能力的通用洞察。我们评估了12个TSFM,并建立了一个多粒度排行榜以促进深入分析和可视化检查。排行榜可在 https://huggingface.co/spaces/Real-TSF/TIME-leaderboard 获取。

英文摘要:

Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation. However, we contend that existing benchmarks exhibit common limitations in four dimensions: constrained data composition dominated by reused legacy sources, compromised data integrity lacking rigorous quality assurance, misaligned task formulations detached from real-world contexts, and rigid analysis perspectives that obscure generalizable insights. To bridge these gaps, we introduce TIME, a next-generation task-centric benchmark comprising 50 fresh datasets and 98 forecasting tasks, tailored for strict zero-shot TSFM evaluation free from data leakage. Integrating large language models and human expertise, we establish a human-in-the-loop benchmark construction pipeline to ensure high data integrity and redefine task formulation by aligning forecasting configurations with real-world operational requirements and variate predictability. Furthermore, we propose a novel pattern-level evaluation perspective that moves beyond traditional dataset-level evaluations based on static meta labels. By leveraging structural time series features to characterize intrinsic temporal properties, this approach offers generalizable insights into model capabilities across diverse patterns. We evaluate 12 TSFMs and establish a multi-granular leaderboard to facilitate in-depth analysis and visualized inspection. The leaderboard is available at https://huggingface.co/spaces/Real-TSF/TIME-leaderboard.

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。

↑