{"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/a-practical-method-for-constructing","title":"A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups","arxiv_id":"2104.09459","date":"2021-04-19","proceeding":null,"authors":["Marc Finzi","Max Welling","Andrew Gordon Wilson"],"abstract":"Symmetries and equivariance are fundamental to the generalization of neural networks on domains such as images, graphs, and point clouds. Existing work has primarily focused on a small number of groups, such as the translation, rotation, and permutation groups. In this work we provide a completely general algorithm for solving for the equivariant layers of matrix groups. In addition to recovering solutions from other works as special cases, we construct multilayer perceptrons equivariant to multiple groups that have never been tackled before, including $\\mathrm{O}(1,3)$, $\\mathrm{O}(5)$, $\\mathrm{Sp}(n)$, and the Rubik's cube group. Our approach outperforms non-equivariant baselines, with applications to particle physics and dynamical systems. We release our software library to enable researchers to construct equivariant layers for arbitrary matrix groups.","url_abs":"https://arxiv.org/abs/2104.09459v1","url_pdf":"https://arxiv.org/pdf/2104.09459v1.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":"a-practical-method-for-constructing","repo_url":"https://github.com/mfinzi/equivariant-MLP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-practical-method-for-constructing","repo_url":"https://github.com/researchworking/scalaremlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-practical-method-for-constructing","repo_url":"https://github.com/weichiyao/scalaremlp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"a-practical-method-for-constructing","repo_url":"https://github.com/zichunhao/lgn-autoencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"rubik-s-cube","task_name":"Rubik's Cube"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.09459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09459"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/researchworking/scalaremlp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/weichiyao/scalaremlp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mfinzi/equivariant-MLP","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zichunhao/lgn-autoencoder","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":9},"by_repo_kind":{"official":{"samples":10,"ran":1,"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":"2660b9d52e1de712","entry":"export","repo":"mfinzi/equivariant-MLP","repo_kind":"official","path":"emlp/utils.py","file_url":"https://github.com/mfinzi/equivariant-MLP/blob/HEAD/emlp/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2660b9d52e1de712"}},{"code_sha256_prefix":"7a51a150eb170ac2","entry":"LBface_swap","repo":"mfinzi/equivariant-MLP","repo_kind":"official","path":"emlp/datasets.py","file_url":"https://github.com/mfinzi/equivariant-MLP/blob/HEAD/emlp/datasets.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":"7a51a150eb170ac2"}},{"code_sha256_prefix":"d867e51e2ce022c2","entry":"UBedge_flip","repo":"mfinzi/equivariant-MLP","repo_kind":"official","path":"emlp/datasets.py","file_url":"https://github.com/mfinzi/equivariant-MLP/blob/HEAD/emlp/datasets.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":"d867e51e2ce022c2"}},{"code_sha256_prefix":"791a506bebdb19cf","entry":"ULBcorner_rot","repo":"mfinzi/equivariant-MLP","repo_kind":"official","path":"emlp/datasets.py","file_url":"https://github.com/mfinzi/equivariant-MLP/blob/HEAD/emlp/datasets.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":"791a506bebdb19cf"}},{"code_sha256_prefix":"7e78a86dc6fd9ae6","entry":"equivariance_err","repo":"mfinzi/equivariant-MLP","repo_kind":"official","path":"experiments/trainer/model_trainer.py","file_url":"https://github.com/mfinzi/equivariant-MLP/blob/HEAD/experiments/trainer/model_trainer.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":"7e78a86dc6fd9ae6"}},{"code_sha256_prefix":"ac065ea6ecd18125","entry":"matrix_power_simple","repo":"mfinzi/equivariant-MLP","repo_kind":"official","path":"emlp/groups.py","file_url":"https://github.com/mfinzi/equivariant-MLP/blob/HEAD/emlp/groups.py","link_basis":"harvester_set","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":"ac065ea6ecd18125"}},{"code_sha256_prefix":"58568c4f4e25b94a","entry":"noise2sample","repo":"mfinzi/equivariant-MLP","repo_kind":"official","path":"emlp/groups.py","file_url":"https://github.com/mfinzi/equivariant-MLP/blob/HEAD/emlp/groups.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":"58568c4f4e25b94a"}},{"code_sha256_prefix":"b9e669d60e5fb206","entry":"rel_err","repo":"mfinzi/equivariant-MLP","repo_kind":"official","path":"emlp/groups.py","file_url":"https://github.com/mfinzi/equivariant-MLP/blob/HEAD/emlp/groups.py","link_basis":"harvester_set","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":"b9e669d60e5fb206"}},{"code_sha256_prefix":"f1110180942acd6b","entry":"rel_err","repo":"mfinzi/equivariant-MLP","repo_kind":"official","path":"experiments/trainer/model_trainer.py","file_url":"https://github.com/mfinzi/equivariant-MLP/blob/HEAD/experiments/trainer/model_trainer.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":"f1110180942acd6b"}},{"code_sha256_prefix":"1c0546beb8cb8de2","entry":"scale_adjusted_rel_err","repo":"mfinzi/equivariant-MLP","repo_kind":"official","path":"experiments/trainer/model_trainer.py","file_url":"https://github.com/mfinzi/equivariant-MLP/blob/HEAD/experiments/trainer/model_trainer.py","link_basis":"harvester_set","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":"1c0546beb8cb8de2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}