用语义增强的MLP-Mixer提升长时序预测多尺度建模能力
SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting
- 引入随机注意力机制与渐进式混合链，增强跨尺度时间依赖建模
- 在10个公开数据集和21GB真实无线网络数据上表现优异，获2025年CCF AlOps挑战赛第三
- 轻量设计适合实际部署，特别适合需要多尺度分析的工业时序场景
长时序时间序列预测（TSF）的关键在于建模多尺度模式。然而，时间序列中的冗余与噪声，以及非相邻尺度间的语义鸿沟，使得高效对齐与整合多尺度时间依赖变得困难。为此，我们提出SEMixer，一种专为长时序TSF设计的轻量级多尺度模型。SEMixer包含两个核心组件：随机注意力机制（RAM）和多尺度渐进混合链（MPMC）。RAM在训练中捕捉多样化的时序块交互，并在推理时通过丢弃集成聚合，增强块级语义，使MLP-Mixer更有效地建模多尺度依赖。MPMC以内存高效方式堆叠RAM与MLP-Mixer，缓解跨尺度语义鸿沟，提升时序混合效果。我们在10个公开数据集及基于21GB真实无线网络数据的2025 CCF AlOps挑战赛中验证了其有效性，取得第三名。代码已开源。
原文摘要 · Abstract (English)
Modeling multiscale patterns is crucial for long-term time series forecasting (TSF). However, redundancy and noise in time series, together with semantic gaps between non-adjacent scales, make the efficient alignment and integration of multi-scale temporal dependencies challenging. To address this, we propose SEMixer, a lightweight multiscale model designed for long-term TSF. SEMixer features two key components: a Random Attention Mechanism (RAM) and a Multiscale Progressive Mixing Chain (MPMC). RAM captures diverse time-patch interactions during training and aggregates them via dropout ensemble at inference, enhancing patch-level semantics and enabling MLP-Mixer to better model multi-scale dependencies. MPMC further stacks RAM and MLP-Mixer in a memory-efficient manner, achieving more effective temporal mixing. It addresses semantic gaps across scales and facilitates better multiscale modeling and forecasting performance. We not only validate the effectiveness of SEMixer on 10 public datasets, but also on the \textit{2025 CCF AlOps Challenge} based on 21GB real wireless network data, where SEMixer achieves third place. The code is available at the link https://github.com/Meteor-Stars/SEMixer.
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。