{"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/equivariance-discovery-by-learned-parameter","title":"Equivariance Discovery by Learned Parameter-Sharing","arxiv_id":"2204.03640","date":"2022-04-07","proceeding":null,"authors":["Raymond A. Yeh","Yuan-Ting Hu","Mark Hasegawa-Johnson","Alexander G. Schwing"],"abstract":"Designing equivariance as an inductive bias into deep-nets has been a prominent approach to build effective models, e.g., a convolutional neural network incorporates translation equivariance. However, incorporating these inductive biases requires knowledge about the equivariance properties of the data, which may not be available, e.g., when encountering a new domain. To address this, we study how to discover interpretable equivariances from data. Specifically, we formulate this discovery process as an optimization problem over a model's parameter-sharing schemes. We propose to use the partition distance to empirically quantify the accuracy of the recovered equivariance. Also, we theoretically analyze the method for Gaussian data and provide a bound on the mean squared gap between the studied discovery scheme and the oracle scheme. Empirically, we show that the approach recovers known equivariances, such as permutations and shifts, on sum of numbers and spatially-invariant data.","url_abs":"https://arxiv.org/abs/2204.03640v1","url_pdf":"https://arxiv.org/pdf/2204.03640v1.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":"equivariance-discovery-by-learned-parameter","repo_url":"https://github.com/raymondyeh07/equivariance_discovery","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.03640","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03640"}},"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/raymondyeh07/equivariance_discovery","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":"12d3e9b47201fb33","entry":"adj_to_set","repo":"raymondyeh07/equivariance_discovery","repo_kind":"official","path":"struct_discovery/evaluation/partition_distance.py","file_url":"https://github.com/raymondyeh07/equivariance_discovery/blob/HEAD/struct_discovery/evaluation/partition_distance.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":"12d3e9b47201fb33"}},{"code_sha256_prefix":"5fcd7bebf475984d","entry":"build_optimizer","repo":"raymondyeh07/equivariance_discovery","repo_kind":"official","path":"struct_discovery/solver/build.py","file_url":"https://github.com/raymondyeh07/equivariance_discovery/blob/HEAD/struct_discovery/solver/build.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":"5fcd7bebf475984d"}},{"code_sha256_prefix":"d8fe2cddae8305b3","entry":"compute_grad","repo":"raymondyeh07/equivariance_discovery","repo_kind":"official","path":"struct_discovery/solver/hypergrad/grad_helpers.py","file_url":"https://github.com/raymondyeh07/equivariance_discovery/blob/HEAD/struct_discovery/solver/hypergrad/grad_helpers.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":"d8fe2cddae8305b3"}},{"code_sha256_prefix":"a74effb2b7707ed5","entry":"conjugate_gradient","repo":"raymondyeh07/equivariance_discovery","repo_kind":"official","path":"struct_discovery/solver/hypergrad/conjugate_gradient.py","file_url":"https://github.com/raymondyeh07/equivariance_discovery/blob/HEAD/struct_discovery/solver/hypergrad/conjugate_gradient.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":"a74effb2b7707ed5"}},{"code_sha256_prefix":"97e7a0b81f740d29","entry":"create_small_table","repo":"raymondyeh07/equivariance_discovery","repo_kind":"official","path":"struct_discovery/utils/logger.py","file_url":"https://github.com/raymondyeh07/equivariance_discovery/blob/HEAD/struct_discovery/utils/logger.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":"97e7a0b81f740d29"}},{"code_sha256_prefix":"e60116082061e5d2","entry":"flatten_param","repo":"raymondyeh07/equivariance_discovery","repo_kind":"official","path":"struct_discovery/solver/hypergrad/grad_helpers.py","file_url":"https://github.com/raymondyeh07/equivariance_discovery/blob/HEAD/struct_discovery/solver/hypergrad/grad_helpers.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":"e60116082061e5d2"}},{"code_sha256_prefix":"06006c69cb12afb4","entry":"my_jacobian","repo":"raymondyeh07/equivariance_discovery","repo_kind":"official","path":"struct_discovery/solver/hypergrad/grad_helpers.py","file_url":"https://github.com/raymondyeh07/equivariance_discovery/blob/HEAD/struct_discovery/solver/hypergrad/grad_helpers.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":"06006c69cb12afb4"}},{"code_sha256_prefix":"6950cdac4f703761","entry":"partition_distance","repo":"raymondyeh07/equivariance_discovery","repo_kind":"official","path":"struct_discovery/evaluation/partition_distance.py","file_url":"https://github.com/raymondyeh07/equivariance_discovery/blob/HEAD/struct_discovery/evaluation/partition_distance.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":"6950cdac4f703761"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}