The numerical solution of partial differential equations (PDEs) is difficult, having led to a century of research so far. Recently, there have been pushes to build neural--numerical hybrid solvers, which piggy-backs the modern trend towards fully end-to-end learned systems. Most works so far can only generalize over a subset of properties to which a generic solver would be faced, including: resolution, topology, geometry, boundary conditions, domain discretization regularity, dimensionality, etc. In this work, we build a solver, satisfying these properties, where all the components are based on neural message passing, replacing all heuristically designed components in the computation graph with backprop-optimized neural function approximators. We show that neural message passing solvers representationally contain some classical methods, such as finite differences, finite volumes, and WENO schemes. In order to encourage stability in training autoregressive models, we put forward a method that is based on the principle of zero-stability, posing stability as a domain adaptation problem. We validate our method on various fluid-like flow problems, demonstrating fast, stable, and accurate performance across different domain topologies, equation parameters, discretizations, etc., in 1D and 2D.
翻译:偏微分方程(PDE)的数值解是困难的,已经进行了一个世纪的研究。最近,人们开始建立神经-数值混合求解器,这样可以利用完全端到端学习系统的现代趋势。迄今为止,大多数工作只能泛化到求解器将面临的属性的一个子集,包括:分辨率、拓扑、几何形状、边界条件、域离散正则性、维数等。在这项工作中,我们建立了一个求解器,满足这些属性,其中所有的组件都基于神经消息传递,用反向传播优化的神经函数逼近器替换计算图中所有的启发式设计组件。我们展示了神经消息传递求解器在表示中包含一些经典方法,如有限差分法、有限体积法和WENO方案。为了鼓励训练自回归模型的稳定性,我们提出了一种基于零稳定性原则的方法,将稳定性作为一个域适应问题。我们验证了我们的方法在各种流体流动问题上的性能,证明了在1D和2D中在不同的域拓扑、方程参数、离散化等方面都具有快速、稳定、精确的性能。