Graph Models


Introduced by Pfaff et al. in Learning Mesh-Based Simulation with Graph Networks

MeshGraphNet is a framework for learning mesh-based simulations using graph neural networks. The model can be trained to pass messages on a mesh graph and to adapt the mesh discretization during forward simulation. The model uses an Encode-Process-Decode architecture trained with one-step supervision, and can be applied iteratively to generate long trajectories at inference time. The encoder transforms the input mesh $M^{t}$ into a graph, adding extra world-space edges. The processor performs several rounds of message passing along mesh edges and world edges, updating all node and edge embeddings. The decoder extracts the acceleration for each node, which is used to update the mesh to produce $M^{t+1}$.

Source: Learning Mesh-Based Simulation with Graph Networks


Paper Code Results Date Stars


Task Papers Share
Numerical Integration 1 100.00%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign