CORGI: GNNs with Convolutional Residual Global Interactions for Lagrangian Simulation
This addresses the challenge of capturing global interactions in fluid dynamics simulations for researchers and practitioners in hydrodynamics, offering a versatile solution with significant performance gains.
The paper tackles the problem of limited receptive fields in Lagrangian neural surrogates for fluid flow simulation by introducing CORGI, a hybrid architecture that augments GNN-based solvers with a lightweight Eulerian component for global context aggregation, achieving improvements such as a 57% increase in rollout accuracy with only 13% more inference time when applied to a GNS backbone.
Partial differential equations (PDEs) are central to dynamical systems modeling, particularly in hydrodynamics, where traditional solvers often struggle with nonlinearity and computational cost. Lagrangian neural surrogates such as GNS and SEGNN have emerged as strong alternatives by learning from particle-based simulations. However, these models typically operate with limited receptive fields, making them inaccurate for capturing the inherently global interactions in fluid flows. Motivated by this observation, we introduce Convolutional Residual Global Interactions (CORGI), a hybrid architecture that augments any GNN-based solver with a lightweight Eulerian component for global context aggregation. By projecting particle features onto a grid, applying convolutional updates, and mapping them back to the particle domain, CORGI captures long-range dependencies without significant overhead. When applied to a GNS backbone, CORGI achieves a 57% improvement in rollout accuracy with only 13% more inference time and 31% more training time. Compared to SEGNN, CORGI improves accuracy by 49% while reducing inference time by 48% and training time by 30%. Even under identical runtime constraints, CORGI outperforms GNS by 47% on average, highlighting its versatility and performance on varied compute budgets.