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 NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Benchmarking | 2 | 28.57% |
Computational Efficiency | 1 | 14.29% |
Fairness | 1 | 14.29% |
Image Classification | 1 | 14.29% |
Meta-Learning | 1 | 14.29% |
Relational Reasoning | 1 | 14.29% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |