HyBDM通过双路径建模全局与局部时序特征，提升多变量时间序列预测精度与效率。
HyBDM: Multi-Scale Hybrid Experts for Time Series Forecasting with Bidirectional Dependency Modeling
- 分两路专家分别捕捉全局模式与局部变化，融合双向卷积与注意力机制。
- 在6个基准数据集上超越现有方法，最高提升4.2%准确率，计算开销更低。
- 适合需要高精度且兼顾推理速度的工业级时间序列预测任务。
时间序列预测对众多应用至关重要，但现有模型常难以同时捕捉多变量时间序列中的异质长程全局模式与短程局部波动。尽管部分方法尝试建模这些依赖关系，却往往未能联合利用时序与通道间信息。为此，我们提出HyBDM，一种多尺度混合专家模型，将时序动态分解为全局模式与局部变化，并由两个专用专家分别建模。全局模式专家采用增强型BiConv-Mamba模块，集成双向卷积、M-SSM层、遗忘机制与GDD-MLP模块以实现跨通道建模；局部变化专家则使用局部窗口变压器（LWT）进行高效局部感知注意力，降低计算复杂度。此外，多尺度分块器与长短路由机制支持多分辨率表征及专家自适应融合。在六个基准数据集上的实验表明，HyBDM在预测精度与计算效率方面均优于当前最优方法，验证了其在弥合全局-局部依赖方面的有效性。
原文摘要 · Abstract (English)
Time series forecasting (TSF) is vital to many applications, yet existing models often struggle to capture the heterogeneous long-range global patterns and short-range local variations in multivariate time series. While some approaches partially model these dependencies, they often do not jointly exploit temporal and feature-wise information. To address this challenge, we propose HyBDM, a multi-scale hybrid model that decomposes temporal dynamics into global patterns and local variations, which are modeled by two specialized experts. The Global Patterns Expert employs an enhanced BiConv-Mamba module that integrates bidirectional convolutions, an M-SSM layer, a forgetting mechanism, and a GDD-MLP module for cross-channel modeling. The Local Variations Expert uses a Local Window Transformer (LWT) to perform efficient locality-aware attention with reduced computational complexity. In addition, a Multi-Scale Patcher and a Long-Short Router enable multi-resolution representations and adaptive fusion of the two experts. Experiments on six benchmark datasets show that HyBDM outperforms state-of-the-art methods in both forecasting accuracy and computational efficiency, demonstrating its effectiveness in bridging global-local dependencies for multivariate TSF.
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。