用简单线性专家模型实现高效高精度时间序列预测
Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting
- 用频率专用线性专家替代深层网络，降低计算开销
- 在多个基准上表现优异，零样本预测准确率超基线
- 适合资源受限场景，且对采样率变化更鲁棒
时间序列预测在能源、金融、医疗和物流等领域至关重要，需具备跨多种数据集的泛化能力。现有大型预训练模型如Chronos和Time-MoE虽具强零样本性能，但计算成本高。本文提出Super-Linear，一种轻量级可扩展的线性专家混合（MoE）模型，以简单频率专用线性专家取代深层结构，并在多频率场景下重采样数据上训练。通过轻量级频谱门控机制动态选择相关专家，实现高效准确的预测。尽管结构简单，其在多个基准上表现良好，显著提升效率、对采样率变化的鲁棒性及可解释性。代码已开源：https://github.com/azencot-group/SuperLinear。
原文摘要 · Abstract (English)
Time series forecasting (TSF) is critical in domains like energy, finance, healthcare, and logistics, requiring models that generalize across diverse datasets. Large pre-trained models such as Chronos and Time-MoE show strong zero-shot (ZS) performance but suffer from high computational costs. In this work, we introduce Super-Linear, a lightweight and scalable mixture-of-experts (MoE) model for general forecasting. It replaces deep architectures with simple frequency-specialized linear experts, trained on resampled data across multiple frequency regimes. A lightweight spectral gating mechanism dynamically selects relevant experts, enabling efficient, accurate forecasting. Despite its simplicity, Super-Linear demonstrates strong performance across benchmarks, while substantially improving efficiency, robustness to sampling rates, and interpretability. The implementation of Super-Linear is available at: \href{https://github.com/azencot-group/SuperLinear}{https://github.com/azencot-group/SuperLinear}.
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。