Domain decomposition methods (DDMs) are popular solvers for discretized systems of partial differential equations (PDEs), with one-level and multilevel variants. These solvers rely on several algorithmic and mathematical parameters, prescribing overlap, subdomain boundary conditions, and other properties of the DDM. While some work has been done on optimizing these parameters, it has mostly focused on the one-level setting or special cases such as structured-grid discretizations with regular subdomain construction. In this paper, we propose multigrid graph neural networks (MG-GNN), a novel GNN architecture for learning optimized parameters in two-level DDMs\@. We train MG-GNN using a new unsupervised loss function, enabling effective training on small problems that yields robust performance on unstructured grids that are orders of magnitude larger than those in the training set. We show that MG-GNN outperforms popular hierarchical graph network architectures for this optimization and that our proposed loss function is critical to achieving this improved performance.
翻译:域分解方法(DDMS)是局部差异方程式离散系统(PDEs)的流行解决方案,具有一级和多级变量。 这些解析器依赖多种算法和数学参数,规定了重叠、次域边界条件以及DDM的其他特性。 虽然在优化这些参数方面已经做了一些工作,但它主要侧重于单级设置或特殊情况,如通过常规子域构建的结构化离散。 在本文件中,我们提出了多格丽格图形神经网络(MG-GNN),这是一个新的GNN结构,用于学习两级DDDMss中的优化参数。我们用新的不受监督的损失功能培训MG-GNNN,以便能够在非结构化的电网中产生强大的性能,而这种电网的规模大于培训的尺寸。我们表明,MG-GNNN为这种优化设计了流行的等级图形网络结构,我们拟议的损失功能对于实现这一改进性能至关重要。</s>