发表机构
ByteDance（字节跳动）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Timer-M1是一种基于基元学习的多元时间序列基础模型，通过开发基元相关的数据合成与预训练流程，在三个大规模预测基准中取得优异成绩，为通用预测技术提供了新路径。
AI 中文摘要
我们提出了Timer-M1，这是一种用于零样本预测的、基于基元学习的预训练多元时间序列基础模型。不同领域的时间序列共享被称为基元的基础时间模式与关系模式，但这些基元在不同上下文的表现与演化方式存在差异。尽管零样本和任务通用预测已取得进展，现有基础模型仍可能难以泛化到复杂真实场景。为此，我们开发了一种基于基元的数据合成与预训练流程：合成流程生成跨领域共享的时间基元序列，再利用关系基元将真实与生成序列组装为多元样本；之后通过分配不同通道角色（目标变量、仅过去协变量、已知未来协变量）将样本组织为训练片段，确保模型利用可用外生信息对可预测变量进行优化。技术上，Timer-M1进一步采用门控二维Transformer块，该块可在各层动态分配跨变量注意力。在三个大规模预测基准测试中，Timer-M1在FEV和TIME指标上排名第一，在GIFT-Eval指标上位列近期时间序列基础模型中的第二。这些结果表明，基于基元的有效预训练是实现跨领域与任务设置的稳健通用预测技术的可行路径。
英文摘要
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.
