用可训练网络替代传统分解，提升时空预测效率与精度。
Robust Spatiotemporal Forecasting Using Adaptive Deep-Unfolded Variational Mode Decomposition
- 将变分模态分解转为固定深度神经模块，提速250倍
- 自适应带宽约束降低95%预测误差，优于现有方法
- 适合需要高效高精度时空预测的工业场景
准确的时空预测对众多复杂系统至关重要，但传统图神经网络存在波动模式复杂、频谱混叠等问题。虽有分解融合方法如变分模态图卷积网络（VMGCN）提升精度，却面临计算效率低和人工调参难题。为此，本文提出模式自适应图网络（MAGN），将迭代式变分模态分解（VMD）转化为可训练的神经模块。核心创新包括：(1) 可展开的变分模态分解（UVMD）模块，以固定深度网络替代迭代优化，使大型时空基准（LargeST）上的分解时间减少250倍；(2) 模式特异性可学习带宽约束（αk），适应空间异质性，消除人工调参并防止频谱重叠。在包含6,902个传感器、2.41亿条观测数据的LargeST基准上，MAGN相比VMGCN实现85%-95%的预测误差降低，性能超越当前最先进模型。
原文摘要 · Abstract (English)
Accurate spatiotemporal forecasting is critical for numerous complex systems but remains challenging due to complex volatility patterns and spectral entanglement in conventional graph neural networks (GNNs). While decomposition-integrated approaches like variational mode graph convolutional network (VMGCN) improve accuracy through signal decomposition, they suffer from computational inefficiency and manual hyperparameter tuning. To address these limitations, we propose the mode adaptive graph network (MAGN) that transforms iterative variational mode decomposition (VMD) into a trainable neural module. Our key innovations include (1) an unfolded VMD (UVMD) module that replaces iterative optimization with a fixed-depth network to reduce the decomposition time (by 250x for the LargeST benchmark), and (2) mode-specific learnable bandwidth constraints (αk ) adapt spatial heterogeneity and eliminate manual tuning while preventing spectral overlap. Evaluated on the LargeST benchmark (6,902 sensors, 241M observations), MAGN achieves an 85-95% reduction in the prediction error over VMGCN and outperforms state-of-the-art baselines.
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。