AI RESEARCH
Efficient Learning of Mesh-Based Physical Simulation with BSMS-GNN
arXiv CS.LG
•
ArXi:2210.02573v5 Announce Type: replace Learning the physical simulation on large-scale meshes with flat Graph Neural Networks (GNNs) and stacking Message Passings (MPs) is challenging due to the scaling complexity w.r.t. the number of nodes and over-smoothing. There has been growing interest in the community to