{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/discovering-symbolic-models-from-deep","title":"Discovering Symbolic Models from Deep Learning with Inductive Biases","arxiv_id":"2006.11287","date":"2020-06-19","proceeding":"NeurIPS 2020 12","authors":["Miles Cranmer","Alvaro Sanchez-Gonzalez","Peter Battaglia","Rui Xu","Kyle Cranmer","David Spergel","Shirley Ho"],"abstract":"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-distribution data better than the GNN itself. Our approach offers alternative directions for interpreting neural networks and discovering novel physical principles from the representations they learn.","url_abs":"https://arxiv.org/abs/2006.11287v2","url_pdf":"https://arxiv.org/pdf/2006.11287v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"discovering-symbolic-models-from-deep","repo_url":"https://github.com/MilesCranmer/PySR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"discovering-symbolic-models-from-deep","repo_url":"https://github.com/MilesCranmer/symbolic_deep_learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"discovering-symbolic-models-from-deep","repo_url":"https://github.com/glouppe/info8010-deep-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"symbolic-regression","task_name":"Symbolic Regression"}],"methods":[{"method_slug":"symbolic-deep-learning","method_name":"Symbolic Deep Learning"}],"datasets_introduced":[],"methods_introduced":[{"slug":"symbolic-deep-learning","name":"Symbolic Deep Learning","full_name":"Symbolic Deep Learning"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2006.11287","atlas_url":"https://app.syntology.ai/?focus=2006.11287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11287"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/MilesCranmer/symbolic_","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/MilesCranmer/symbolic_deep_learning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/glouppe/info8010-deep-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MilesCranmer/PySR","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7588e3973fd7c9ef","entry":"HGN","repo":"milescranmer/symbolic_deep_learning","repo_kind":"official","path":"models.py","file_url":"https://github.com/milescranmer/symbolic_deep_learning/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7588e3973fd7c9ef"}},{"code_sha256_prefix":"4a743e335d590994","entry":"get_edge_index","repo":"MilesCranmer/symbolic_deep_learning","repo_kind":"official","path":"models.py","file_url":"https://github.com/MilesCranmer/symbolic_deep_learning/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4a743e335d590994"}},{"code_sha256_prefix":"5ee9e6fbe51118a9","entry":"get_potential","repo":"MilesCranmer/symbolic_deep_learning","repo_kind":"official","path":"simulate.py","file_url":"https://github.com/MilesCranmer/symbolic_deep_learning/blob/HEAD/simulate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ee9e6fbe51118a9"}},{"code_sha256_prefix":"a54f8c6edea8287c","entry":"make_packer","repo":"MilesCranmer/symbolic_deep_learning","repo_kind":"official","path":"models.py","file_url":"https://github.com/MilesCranmer/symbolic_deep_learning/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a54f8c6edea8287c"}},{"code_sha256_prefix":"d972129611261eaf","entry":"make_transparent_color","repo":"MilesCranmer/symbolic_deep_learning","repo_kind":"official","path":"simulate.py","file_url":"https://github.com/MilesCranmer/symbolic_deep_learning/blob/HEAD/simulate.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d972129611261eaf"}},{"code_sha256_prefix":"54e73a14a67ebd62","entry":"make_unpacker","repo":"MilesCranmer/symbolic_deep_learning","repo_kind":"official","path":"models.py","file_url":"https://github.com/MilesCranmer/symbolic_deep_learning/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"54e73a14a67ebd62"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}