{"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/svcca-singular-vector-canonical-correlation","title":"SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability","arxiv_id":"1706.05806","date":"2017-06-19","proceeding":"NeurIPS 2017 12","authors":["Maithra Raghu","Justin Gilmer","Jason Yosinski","Jascha Sohl-Dickstein"],"abstract":"We propose a new technique, Singular Vector Canonical Correlation Analysis\n(SVCCA), a tool for quickly comparing two representations in a way that is both\ninvariant to affine transform (allowing comparison between different layers and\nnetworks) and fast to compute (allowing more comparisons to be calculated than\nwith previous methods). We deploy this tool to measure the intrinsic\ndimensionality of layers, showing in some cases needless over-parameterization;\nto probe learning dynamics throughout training, finding that networks converge\nto final representations from the bottom up; to show where class-specific\ninformation in networks is formed; and to suggest new training regimes that\nsimultaneously save computation and overfit less. Code:\nhttps://github.com/google/svcca/","url_abs":"http://arxiv.org/abs/1706.05806v2","url_pdf":"http://arxiv.org/pdf/1706.05806v2.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":"svcca-singular-vector-canonical-correlation","repo_url":"https://github.com/google/svcca","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"svcca-singular-vector-canonical-correlation","repo_url":"https://github.com/delve-team/delve","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"svcca-singular-vector-canonical-correlation","repo_url":"https://github.com/moskomule/cca.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.05806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.05806"}},"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/delve-team/delve","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google/svcca","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/moskomule/cca.pytorch","reach":null}],"summary":{"ran_fixture":3,"ran_honours":1,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"listed":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"01472465bed8b268","entry":"compute_ccas","repo":"google/svcca","repo_kind":"official","path":"cca_core.py","file_url":"https://github.com/google/svcca/blob/HEAD/cca_core.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"01472465bed8b268"}},{"code_sha256_prefix":"ea98389a1755bb3f","entry":"positivedef_matrix_sqrt","repo":"google/svcca","repo_kind":"official","path":"cca_core.py","file_url":"https://github.com/google/svcca/blob/HEAD/cca_core.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ea98389a1755bb3f"}},{"code_sha256_prefix":"ffcbd13c7094948e","entry":"remove_small","repo":"google/svcca","repo_kind":"official","path":"cca_core.py","file_url":"https://github.com/google/svcca/blob/HEAD/cca_core.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ffcbd13c7094948e"}},{"code_sha256_prefix":"38d282dc70b65fd7","entry":"svcca_distance","repo":"moskomule/cca.pytorch","repo_kind":"listed","path":"cca/cca.py","file_url":"https://github.com/moskomule/cca.pytorch/blob/HEAD/cca/cca.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"38d282dc70b65fd7"}},{"code_sha256_prefix":"25452d41e8e4d737","entry":"svd_reduction","repo":"moskomule/cca.pytorch","repo_kind":"listed","path":"cca/cca.py","file_url":"https://github.com/moskomule/cca.pytorch/blob/HEAD/cca/cca.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"25452d41e8e4d737"}},{"code_sha256_prefix":"eff74a29f37795b8","entry":"zero_mean","repo":"moskomule/cca.pytorch","repo_kind":"listed","path":"cca/cca.py","file_url":"https://github.com/moskomule/cca.pytorch/blob/HEAD/cca/cca.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eff74a29f37795b8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}