Graph Models

Graph Network-based Simulators

Introduced by Sanchez-Gonzalez et al. in Learning to Simulate Complex Physics with Graph Networks

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.

Source: Learning to Simulate Complex Physics with Graph Networks

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Graph Neural Network 5 33.33%
Computational Efficiency 2 13.33%
Benchmarking 2 13.33%
Pose Estimation 1 6.67%
Quantization 1 6.67%
Fairness 1 6.67%
Image Classification 1 6.67%
Meta-Learning 1 6.67%
Relational Reasoning 1 6.67%

Components


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

Categories