{"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/repairing-systematic-outliers-by-learning-1","title":"Repairing Systematic Outliers by Learning Clean Subspaces in VAEs","arxiv_id":"2207.08050","date":"2022-07-17","proceeding":null,"authors":["Simao Eduardo","Kai Xu","Alfredo Nazabal","Charles Sutton"],"abstract":"Data cleaning often comprises outlier detection and data repair. Systematic errors result from nearly deterministic transformations that occur repeatedly in the data, e.g. specific image pixels being set to default values or watermarks. Consequently, models with enough capacity easily overfit to these errors, making detection and repair difficult. Seeing as a systematic outlier is a combination of patterns of a clean instance and systematic error patterns, our main insight is that inliers can be modelled by a smaller representation (subspace) in a model than outliers. By exploiting this, we propose Clean Subspace Variational Autoencoder (CLSVAE), a novel semi-supervised model for detection and automated repair of systematic errors. The main idea is to partition the latent space and model inlier and outlier patterns separately. CLSVAE is effective with much less labelled data compared to previous related models, often with less than 2% of the data. We provide experiments using three image datasets in scenarios with different levels of corruption and labelled set sizes, comparing to relevant baselines. CLSVAE provides superior repairs without human intervention, e.g. with just 0.25% of labelled data we see a relative error decrease of 58% compared to the closest baseline.","url_abs":"https://arxiv.org/abs/2207.08050v1","url_pdf":"https://arxiv.org/pdf/2207.08050v1.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":"repairing-systematic-outliers-by-learning-1","repo_url":"https://github.com/sfme/clsvae-error-repair","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"outlier-detection","task_name":"Outlier Detection"}],"methods":[{"method_slug":"repair","method_name":"Repair"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.08050","atlas_url":"https://app.syntology.ai/?focus=2207.08050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08050"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sfme/clsvae-error-repair","reach":null}],"summary":{"ran":5,"ran_draft_wrong":9,"ran_honours":1,"ran_fixture":1,"unverified":4},"by_repo_kind":{"official":{"samples":19,"ran":15,"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":1,"samples":[{"code_sha256_prefix":"8481946e737c208b","entry":"BernoulliDistModule","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","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":"8481946e737c208b"}},{"code_sha256_prefix":"cfb56fff21e907ec","entry":"GaussDiagDistModule","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","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":"cfb56fff21e907ec"}},{"code_sha256_prefix":"531f02e64d7cb8c2","entry":"baseDecoder","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"531f02e64d7cb8c2"}},{"code_sha256_prefix":"a49e297e81d9704b","entry":"baseEncoder","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","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":"a49e297e81d9704b"}},{"code_sha256_prefix":"e043d45b15d6b755","entry":"distance_correlation","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e043d45b15d6b755"}},{"code_sha256_prefix":"53481f45062c91b6","entry":"kl_bern","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"53481f45062c91b6"}},{"code_sha256_prefix":"e9f356ae0089c419","entry":"kl_gauss_diag","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9f356ae0089c419"}},{"code_sha256_prefix":"5dad1c9bfeeba510","entry":"logit_fn","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5dad1c9bfeeba510"}},{"code_sha256_prefix":"f44725a1fe393af6","entry":"masker","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f44725a1fe393af6"}},{"code_sha256_prefix":"b6cc480db383d7f8","entry":"merge_leading_dims","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b6cc480db383d7f8"}},{"code_sha256_prefix":"015859f1f739f8d4","entry":"modSeq","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"015859f1f739f8d4"}},{"code_sha256_prefix":"8f191236fc907a34","entry":"nll_binary_global","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8f191236fc907a34"}},{"code_sha256_prefix":"d4257574f5fb26e9","entry":"nll_categ_global","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d4257574f5fb26e9"}},{"code_sha256_prefix":"494226cd33056112","entry":"nll_gauss_global","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"494226cd33056112"}},{"code_sha256_prefix":"82ebdfc64ea97bb7","entry":"repeat_rows","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"82ebdfc64ea97bb7"}},{"code_sha256_prefix":"a27183852b672b4c","entry":"split_leading_dim","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a27183852b672b4c"}},{"code_sha256_prefix":"7b62da118d40ebcf","entry":"VAE","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.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":"7b62da118d40ebcf"}},{"code_sha256_prefix":"4084058cfba14167","entry":"nll_batch_noreduce","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.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":"4084058cfba14167"}},{"code_sha256_prefix":"93debe3df0d62ace","entry":"semi_y_vae_partitioned_ELBO","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.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":"93debe3df0d62ace"}},{"code_sha256_prefix":"ecb04549beebc113","entry":"y_weighted_nll","repo":"sfme/clsvae-error-repair","repo_kind":"official","path":"src/repair_syserr_models/semi_y_CLSVAE.py","file_url":"https://github.com/sfme/clsvae-error-repair/blob/HEAD/src/repair_syserr_models/semi_y_CLSVAE.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":"ecb04549beebc113"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}