arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.22586cs.LG
收藏

为上下文条件时间序列任务构建一个基础模型

A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks

Walmart(沃尔玛)

Anish Saha, Konstantin Shmakov

AI总结:

本文提出iAmTime模型,通过指令条件化的元学习实现时间序列任务的直接推理,提升零样本适应能力,尤其在预测任务中表现优异。

摘要:

上下文学习(ICL)通过在推理时依赖演示而非更新模型参数来实现任务适应。尽管最近的时间序列基础模型集成了上下文条件、检索或基于示例的提示,但它们通常依赖于隐含的位置结构或任务特定的目标,而非显式的指令条件输入输出演示。我们引入iAmTime,一个通过指令条件化的元学习训练的时间序列基础模型,能够直接从示例演示中推断任务。iAmTime将每个episode表示为基于历史上下文和未来已知变量的结构化提示,使用专门的语义标记来关注指定的时间序列区域,跨演示交换信息,并将任务信息注入查询表示中。该模型结合了层次多视角Transformer编码器,该编码器在推断潜在任务结构时捕捉时间动态和协变量动态,以及任务条件化的补丁解码器,通过专家路由进行解码适应。我们使用监督和自监督的指令条件任务在大规模真实和合成语料库上训练iAmTime,包括预测、填补、重建、分类、异常检测和源分离。在各种领域、频率和时间范围内,iAmTime在概率和点预测基准上优于强大的时间序列基础基线,在非预测任务如分类中也实现了竞争性性能。

英文摘要:

In-context learning (ICL) enables task adaptation at inference time by conditioning on demonstrations rather than updating model parameters. Although recent time-series foundation models incorporate contextual conditioning, retrieval, or example-based prompting, they typically rely on implicit positional structure or task-specific objectives rather than explicit instruction-conditioned input-output demonstrations. We introduce iAmTime, a time-series foundation model trained with instruction-conditioned amortized meta-learning to infer tasks directly from example demonstrations. iAmTime represents each episode as a structured prompt over historical context and future-known variables using specialized semantic tokens that attend to designated time-series regions, exchange information across demonstrations, and inject task information into the query representation. The model combines a Hierarchical Multi-Scope Transformer Encoder, which captures temporal and covariate dynamics while inferring latent task structure from demonstrated input-output mappings, with a Task-Conditioned Patch Decoder, which adapts decoding through expert-based routing. We train iAmTime on large-scale real and synthetic corpora using supervised and self-supervised instruction-conditioned tasks, including forecasting, imputation, reconstruction, classification, anomaly detection, and source de-mixing. Across diverse domains, frequencies, and horizons, iAmTime improves zero-shot adaptation over strong time-series foundation baselines on probabilistic and point forecasting benchmarks, while achieving competitive or superior performance on four non-forecasting tasks.

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。

↑