We lifted 1 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| tumaer/sph-hae | canonical | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| avg_initialization | Not yet run | tumaer/sph-hae/sph_hae/haesegnn.py code served (permissive licence) · get_code("41f41f3ebf2432c1") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We contribute to the vastly growing field of machine learning for engineering systems by demonstrating that equivariant graph neural networks have the potential to learn more accurate dynamic-interaction models than their non-equivariant counterparts. We benchmark two well-studied fluid-flow systems, namely 3D decaying Taylor-Green vortex and 3D reverse Poiseuille flow, and evaluate the models based on different performance measures, such as kinetic energy or Sinkhorn distance. In addition, we investigate different embedding methods of physical-information histories for equivariant models. We find that while currently being rather slow to train and evaluate, equivariant models with our proposed history embeddings learn more accurate physical interactions.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2305.15603")
get_code_for_paper("2305.15603")
have("2305.15603")
Connect an agent — have() is free.