Description
Graph Network-Based Simulators is a type of graph neural network that represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing.
Papers Using This Method
Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers2024-11-01MBDS: A Multi-Body Dynamics Simulation Dataset for Graph Networks Simulators2024-10-04UAV-Enabled Data Collection for IoT Networks via Rainbow Learning2024-09-22Learning to Simulate Aerosol Dynamics with Graph Neural Networks2024-09-20Finite-difference-informed graph network for solving steady-state incompressible flows on block-structured grids2024-06-15Asymptotic Unbiased Sample Sampling to Speed Up Sharpness-Aware Minimization2024-06-12Adaptive Graph Normalized Sign Algorithm2024-05-07Inverse analysis of granular flows using differentiable graph neural network simulator2024-01-17Three-dimensional granular flow simulation using graph neural network-based learned simulator2023-11-13LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite2023-09-28Accelerating Particle and Fluid Simulations with Differentiable Graph Networks for Solving Forward and Inverse Problems2023-09-23Graph Neural Network-based surrogate model for granular flows2023-05-09GNS: A generalizable Graph Neural Network-based simulator for particulate and fluid modeling2022-11-18Cost-Efficient Deployment of a Reliable Multi-UAV Unmanned Aerial System2022-08-30Fairness Based Energy-Efficient 3D Path Planning of a Portable Access Point: A Deep Reinforcement Learning Approach2022-08-10Minority Report: A Graph Network Oracle for In Situ Visualization2022-06-25Subspace Graph Physics: Real-Time Rigid Body-Driven Granular Flow Simulation2021-11-18Manipulation of Granular Materials by Learning Particle Interactions2021-11-03Learning to Schedule Learning rate with Graph Neural Networks2021-09-29Relational VAE: A Continuous Latent Variable Model for Graph Structured Data2021-06-30