TimePro通过动态感知变量与时间，提升长期多变量预测精度
TimePro: Efficient Multivariate Long-term Time Series Forecasting with Variable- and Time-Aware Hyper-state
- 引入可变与时间感知的超状态机制，动态聚焦关键时间点
- 在8个真实数据集上表现优于主流模型，计算复杂度线性增长
- 适合需要精准捕捉多变量时滞关系的工业预测场景
在长期时间序列预测中，不同变量对目标变量的影响往往发生在不同时间区间，这一现象称为多延迟问题。传统模型通常对所有变量或时间点进行统一处理，难以捕捉复杂的变量关系并获得有意义的时间表示。为此，我们提出TimePro，一种基于Mamba的创新模型，构建变量与时间感知的超状态。不同于仅在变量或时间维度传递原始状态的传统方法，TimePro保留每个变量标记的细粒度时间特征，并自适应选择关注的时间点以调整原始状态。重构后的超状态能同时感知变量间关系与关键时间信息，从而提升预测准确性。实验表明，TimePro在八个真实世界长期预测基准上表现优异，具备令人满意的线性复杂度。代码已开源：https://github.com/xwmaxwma/TimePro。
原文摘要 · Abstract (English)
In long-term time series forecasting, different variables often influence the target variable over distinct time intervals, a challenge known as the multi-delay issue. Traditional models typically process all variables or time points uniformly, which limits their ability to capture complex variable relationships and obtain non-trivial time representations. To address this issue, we propose TimePro, an innovative Mamba-based model that constructs variate- and time-aware hyper-states. Unlike conventional approaches that merely transfer plain states across variable or time dimensions, TimePro preserves the fine-grained temporal features of each variate token and adaptively selects the focused time points to tune the plain state. The reconstructed hyper-state can perceive both variable relationships and salient temporal information, which helps the model make accurate forecasting. In experiments, TimePro performs competitively on eight real-world long-term forecasting benchmarks with satisfactory linear complexity. Code is available at https://github.com/xwmaxwma/TimePro.
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。