用动态记忆缓冲提升多尺度图神经网络的预测精度
Reducing Smoothness with Expressive Memory Enhanced Hierarchical Graph Neural Networks
- 引入动态大小记忆缓冲，保留跨尺度变量信息
- 在多个数据集上平均降低6.1% MAE、6.2% RMSE
- 适合气象等需要多分辨率建模的任务
图模型通过投影到图结构来学习时间序列的结构，近期方法利用边权重捕捉变量间的时空关联。层级化模型通过在多分辨率下分析时间序列获得优势，尤其适用于全球天气预报等任务。层级模型面临前向或反向传播中的信息丢失问题。我们提出层次图流（HiGFlow）网络，引入动态大小的记忆缓冲变量，以存储不同分辨率下的历史信息。理论上证明：HiGFlow在映射到层次中新特征空间时降低平滑性，并非严格增强消息传递的效用，通过提升Weisfeiler-Lehman（WL）表达能力实现。实验表明，相比最先进基线（包括变换器模型），HiGFlow在平均MAE上至少提升6.1%，在RMSE上至少提升6.2%。代码已开源：https://github.com/TB862/HiGFlow.git。
原文摘要 · Abstract (English)
Graphical forecasting models learn the structure of time series data via projecting onto a graph, with recent techniques capturing spatial-temporal associations between variables via edge weights. Hierarchical variants offer a distinct advantage by analysing the time series across multiple resolutions, making them particularly effective in tasks like global weather forecasting, where low-resolution variable interactions are significant. A critical challenge in hierarchical models is information loss during forward or backward passes through the hierarchy. We propose the Hierarchical Graph Flow (HiGFlow) network, which introduces a memory buffer variable of dynamic size to store previously seen information across variable resolutions. We theoretically show two key results: HiGFlow reduces smoothness when mapping onto new feature spaces in the hierarchy and non-strictly enhances the utility of message-passing by improving Weisfeiler-Lehman (WL) expressivity. Empirical results demonstrate that HiGFlow outperforms state-of-the-art baselines, including transformer models, by at least an average of 6.1% in MAE and 6.2% in RMSE. Code is available at https://github.com/TB862/ HiGFlow.git.
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。