Jiatong Han
We lifted 4 functions out of this paper's own repositories and ran 1 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 |
|---|---|---|
| jthh/many-body-mpnn | canonical | 1 of 4 |
| Function | Status | Where it lives |
|---|---|---|
| compute_loss | Ran | jthh/many-body-mpnn/utils.py pointer only (licence: NONE) · get_code("85f5e308f40e82df") |
| evaluate | Not yet run | jthh/many-body-mpnn/utils.py pointer only (licence: NONE) · get_code("0cc26e3d0c7cfdb6") |
| load_zinc_dataset_subset | Not yet run | jthh/many-body-mpnn/datasets.py pointer only (licence: NONE) · get_code("d1b77dba28462fd2") |
| train | Not yet run | jthh/many-body-mpnn/utils.py pointer only (licence: NONE) · get_code("4dd698b1c78ec59a") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We present many-body Message Passing Neural Network (MPNN) framework that models higherorder node interactions (≥ 2 nodes). We model higher-order terms as tree-shaped motifs, comprising a central node with its neighborhood, and apply localized spectral filters on motif Laplacian, weighted by global edge Ricci curvatures. We prove our formulation is invariant to neighbor node permutation, derive its sensitivity bound, and bound the range of learned graph potential. We run regression on graph energies to demonstrate that it scales well with deeper and wider network topology, and run classification on synthetic graph datasets with heterophily and show its consistently high Dirichlet energy growth. We open-source our code at https://github. com/JThh/Many-Body-MPNN.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.11756")
get_code_for_paper("2407.11756")
have("2407.11756")
Connect an agent — have() is free.