一个统一模型，能按约束生成多领域时间序列。
UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation
- 用提示词控制的统一语言模型，替代各数据集专用模型。
- 在4个真实数据集上实现峰值、负荷等模式精准生成。
- 适合需要跨域生成与小样本数据增强的研究者。
在时间序列生成中，现有方法通常为每个数据集手工设计或训练独立模型，限制了可扩展性且未能利用不同领域间的共享时序结构。为此，我们提出UPLOTS——一个面向跨领域约束时间序列生成的统一预训练语言模型框架。不同于构建任务专用模型，UPLOTS采用单一预训练Transformer主干网络，通过学习到的约束提示词进行引导，实现在推理时按需生成并精确控制模式。其关键创新在于动态多数据集损失重加权与提示词-模式映射机制，使模型在训练中内化多样时序结构，并在推理时条件化生成。我们在四个真实世界基准和多种约束设置（包括峰值期、日历、负载水平、波动性模式）上评估了UPLOTS。额外的保留约束组合及下游预测实验进一步表明，UPLOTS不仅泛化至原始峰值模式之外，还在真实数据稀缺场景下提升数据增强效果。代码与基线已开源于GitHub：https://github.com/cruiseresearchgroup/UPLOTS。
原文摘要 · Abstract (English)
In time-series generation, existing approaches typically handcraft ortrain a separate model for each dataset, which hinders their scalability and fails to leverage shared temporal structures across domains. To address this fragmentation, we propose UPLOTS, a Unified, Prompt-guided Language model framework fOr constrained Time-Series Generation across diverse domains. Instead of building task-specific models, UPLOTS leverages a single pre-trained transformer backbone guided by learned constraint prompts, enabling on-demand generation with precise pattern control. One key innovation is our dynamic multi-dataset loss re-weighting and prompt-to-pattern mapping, which allows UPLOTS to internalize diverse temporal structures during training and conditionally generate them at inference. We evaluate UPLOTS on four real-world benchmarks and multiple constraint settings, including peak-period, calendar, load-level, and volatility patterns. Additional held-out constraint-combination and downstream forecasting experiments further demonstrate that UPLOTS generalizes beyond the original peak-pattern setting and improves data augmentation under scarce real-data regimes. Our code and baselines are available at github repo: https://github.com/cruiseresearchgroup/UPLOTS.
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。