发表机构
Lawrence Berkeley National Laboratory; Stanford University; Pacific Northwest National Laboratory（劳伦斯伯克利国家实验室; 斯坦福大学; 太平洋西北国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TWIG是一种图原生时间因果小波算子，通过因果多尺度特征与图小波块实现不规则图上的稳定自回归预测，在多个基准上优于非因果基线。
AI 中文摘要
我们提出了TWIG（面向不规则图的时间因果小波算子），一种用于静态不规则图上自回归代理建模的图原生神经算子。TWIG将每个节点的历史转化为因果多尺度时间特征，将近期变化与逐渐变慢的记忆成分分离，然后通过带有门控逐点通道混合的图小波算子块传播这些特征。该架构在构造上具有因果性，专为闭环预测设计，其中预测结果被递归地用作未来输入。我们在三个不规则域预测问题上评估了TWIG，涵盖区域扩散、三维地下水文和空气动力学流动，图规模从400到5,233个节点，模型容量从约70k到1000万参数。TWIG在地下水文和区域扩散基准上取得了最低的累计滚动误差，并在1000万参数的空气动力学流动基准上排名第二，仅次于GPS Transformer。在所有三个设置中，TWIG始终优于相应的非时间因果图WNO基线。这些结果表明，TWIG为不规则图上动力场的稳定自回归预测提供了一种有效且可扩展的方法。
英文摘要
We introduce TWIG (Time-Causal Wavelet Operator for Irregular Graphs), a graph-native neural operator for autoregressive surrogate modeling on static irregular graphs. TWIG transforms each node history into causal multiscale temporal features that separate recent variation from progressively slower memory components, then propagates these features through graph-wavelet operator blocks with gated pointwise channel mixing. The architecture is causal by construction and designed for closed-loop forecasting, where predictions are recursively reused as future inputs. We evaluate TWIG on three irregular-domain forecasting problems spanning regional diffusion, three-dimensional subsurface hydrology, and aerodynamic flow, with graphs ranging from 400 to 5,233 nodes and model capacities from approximately 70k to 10M parameters. TWIG achieves the lowest aggregate rollout errors on the subsurface-hydrology and regional-diffusion benchmarks and ranks second on the 10M-parameter aerodynamic-flow benchmark, behind the GPS Transformer. Across all three settings, TWIG consistently outperforms the corresponding non-time-causal Graph WNO baseline. These results demonstrate that TWIG provides an effective and scalable approach to stable autoregressive forecasting of dynamical fields on irregular graphs.
Comments23 pages, 5 figures. Preprint
