arXiv cs.AI· Haoran Zhang, Haixuan Liu, Xingjian Su, Yong Liu, Zhi Chen, Yuxuan Wang, Jianmin Wang, Mingsheng Long·· 9 天前AI 评分27
Timer-M1：通过学习基元构建的多变量时间序列基础模型
Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives
AI 导读
Timer-M1 是一个基于基元学习的预训练多变量时间序列基础模型，用于零样本预测。它通过基元数据合成与预训练流程，结合门控二维 Transformer 模块动态分配跨变量注意力。在 FEV 和 TIME 两个大规模预测基准上排名第一，GIFT-Eval 上排名第二。
正文 · 原文
Abstract:We introduce Timer-M1, a pretrained multivariate time series foundation model that learns with primitives for zero-shot forecasting. Across domains, time series share elementary temporal and relational patterns, termed primitives, yet differ in how these primitives manifest and evolve across different contexts. Despite progress in zero-shot and task-general forecasting, existing foundation models may still struggle to generalize to complex real-world scenarios. To this end, we develop a primitive-based data synthesis and pretraining pipeline. The synthesis pipeline generates series with temporal primitives shared across domains and then assembles real and generated series into multivariate samples using relational primitives. Afterwards, samples are organized into episodes by assigning distinct channel roles as target variates, past-only covariates, and known-future covariates, ensuring that the model is optimized on predictable variates using available exogenous information. Technically, Timer-M1 further adapts gated two-dimensional Transformer blocks that dynamically allocate cross-variate attention across layers. Across three large-scale forecasting benchmarks, Timer-M1 ranks first on both FEV and TIME and second on GIFT-Eval among most recent time series foundation models. These results support effective primitive-based pretraining as a route to robust general forecasting technique across domains and task settings.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11734 [cs.LG] |
| (or arXiv:2610.11734v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11734 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Haoran Zhang [view email]
[v1]
Thu, 8 Oct 2026 11:28:56 UTC (1,326 KB)
来源：arXiv cs.AI · arxiv.org