Kyle Cranmer, Alvaro Sanchez-Gonzalez, Peter Battaglia, Miles Cranmer, David Spergel, Shirley Ho, Rui Xu
We lifted 6 functions out of this paper's own repositories and ran 5 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 |
|---|---|---|
| MilesCranmer/symbolic_deep_learning | canonical | 5 of 5 |
| milescranmer/symbolic_deep_learning | canonical | 0 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| get_edge_index | Ran | MilesCranmer/symbolic_deep_learning/models.py code served (permissive licence) · get_code("4a743e335d590994") |
| get_potential | Ran | MilesCranmer/symbolic_deep_learning/simulate.py code served (permissive licence) · get_code("5ee9e6fbe51118a9") |
| make_packer | Ran | MilesCranmer/symbolic_deep_learning/models.py code served (permissive licence) · get_code("a54f8c6edea8287c") |
| make_transparent_color | Ran | MilesCranmer/symbolic_deep_learning/simulate.py code served (permissive licence) · get_code("d972129611261eaf") |
| make_unpacker | Ran | MilesCranmer/symbolic_deep_learning/models.py code served (permissive licence) · get_code("54e73a14a67ebd62") |
| HGN | Not yet run | milescranmer/symbolic_deep_learning/models.py code served (permissive licence) · get_code("7588e3973fd7c9ef") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We develop a general approach to distill symbolic representations of a learned deep model by introducing strong inductive biases. We focus on Graph Neural Networks (GNNs). The technique works as follows: we first encourage sparse latent representations when we train a GNN in a supervised setting, then we apply symbolic regression to components of the learned model to extract explicit physical relations. We find the correct known equations, including force laws and Hamiltonians, can be extracted from the neural network. We then apply our method to a non-trivial cosmology example-a detailed dark matter simulation-and discover a new analytic formula which can predict the concentration of dark matter from the mass distribution of nearby cosmic structures. The symbolic expressions extracted from the GNN using our technique also generalized to out-of-distributiondata better than the GNN itself. Our approach offers alternative directions for interpreting neural networks and discovering novel physical principles from the representations they learn. Code for our models and experiments can be found at https://github.com/MilesCranmer/symbolic_ deep_learning.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2006.11287")
get_code_for_paper("2006.11287")
have("2006.11287")
Connect an agent — have() is free.