{"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-probabilistic-approach-to-learning-the","title":"A Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs","arxiv_id":"2406.03946","date":"2024-06-06","proceeding":null,"authors":["Lars Veefkind","Gabriele Cesa"],"abstract":"Steerable convolutional neural networks (SCNNs) enhance task performance by modelling geometric symmetries through equivariance constraints on weights. Yet, unknown or varying symmetries can lead to overconstrained weights and decreased performance. To address this, this paper introduces a probabilistic method to learn the degree of equivariance in SCNNs. We parameterise the degree of equivariance as a likelihood distribution over the transformation group using Fourier coefficients, offering the option to model layer-wise and shared equivariance. These likelihood distributions are regularised to ensure an interpretable degree of equivariance across the network. Advantages include the applicability to many types of equivariant networks through the flexible framework of SCNNs and the ability to learn equivariance with respect to any subgroup of any compact group without requiring additional layers. Our experiments reveal competitive performance on datasets with mixed symmetries, with learnt likelihood distributions that are representative of the underlying degree of equivariance.","url_abs":"https://arxiv.org/abs/2406.03946v3","url_pdf":"https://arxiv.org/pdf/2406.03946v3.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-probabilistic-approach-to-learning-the","repo_url":"https://github.com/QUVA-Lab/partial-escnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause-Clear"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.03946","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03946"}},"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/QUVA-Lab/partial-escnn","reach":{"status":"ok","spdx":"BSD-3-Clause-Clear"}}],"summary":{"ran":9},"by_repo_kind":{"official":{"samples":9,"ran":9,"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":9,"samples":[{"code_sha256_prefix":"f87f6cbd9148db68","entry":"add_ones","repo":"QUVA-Lab/partial-escnn","repo_kind":"official","path":"networks/pointcnn.py","file_url":"https://github.com/QUVA-Lab/partial-escnn/blob/HEAD/networks/pointcnn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"f87f6cbd9148db68"}},{"code_sha256_prefix":"5359df1abd00794a","entry":"bandlimiting_filter","repo":"QUVA-Lab/partial-escnn","repo_kind":"official","path":"escnn2/r2convolution.py","file_url":"https://github.com/QUVA-Lab/partial-escnn/blob/HEAD/escnn2/r2convolution.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"5359df1abd00794a"}},{"code_sha256_prefix":"54c6b49ca1677801","entry":"bandlimiting_filter","repo":"QUVA-Lab/partial-escnn","repo_kind":"official","path":"escnn2/r3convolution.py","file_url":"https://github.com/QUVA-Lab/partial-escnn/blob/HEAD/escnn2/r3convolution.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"54c6b49ca1677801"}},{"code_sha256_prefix":"83fd42dceecd1363","entry":"compute_basis_params","repo":"QUVA-Lab/partial-escnn","repo_kind":"official","path":"escnn2/r2convolution.py","file_url":"https://github.com/QUVA-Lab/partial-escnn/blob/HEAD/escnn2/r2convolution.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"83fd42dceecd1363"}},{"code_sha256_prefix":"0100653e23861125","entry":"compute_basis_params","repo":"QUVA-Lab/partial-escnn","repo_kind":"official","path":"escnn2/r3convolution.py","file_url":"https://github.com/QUVA-Lab/partial-escnn/blob/HEAD/escnn2/r3convolution.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"0100653e23861125"}},{"code_sha256_prefix":"c660e35bb41e7b32","entry":"create_config","repo":"QUVA-Lab/partial-escnn","repo_kind":"official","path":"experiments/eval_model.py","file_url":"https://github.com/QUVA-Lab/partial-escnn/blob/HEAD/experiments/eval_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"c660e35bb41e7b32"}},{"code_sha256_prefix":"5d17f6f10a0d9dca","entry":"get_grid_coords","repo":"QUVA-Lab/partial-escnn","repo_kind":"official","path":"escnn2/rd_convolution.py","file_url":"https://github.com/QUVA-Lab/partial-escnn/blob/HEAD/escnn2/rd_convolution.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"5d17f6f10a0d9dca"}},{"code_sha256_prefix":"73fde12c36f4e5ba","entry":"make_batch","repo":"QUVA-Lab/partial-escnn","repo_kind":"official","path":"networks/pointcnn.py","file_url":"https://github.com/QUVA-Lab/partial-escnn/blob/HEAD/networks/pointcnn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"73fde12c36f4e5ba"}},{"code_sha256_prefix":"1ef7ee42395e08bc","entry":"make_batch_","repo":"QUVA-Lab/partial-escnn","repo_kind":"official","path":"networks/pointcnn.py","file_url":"https://github.com/QUVA-Lab/partial-escnn/blob/HEAD/networks/pointcnn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause-Clear","inline_ok":false,"mcp_get_code":{"code_sha256":"1ef7ee42395e08bc"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}