Papers › Repairing Systematic Outliers by Learning Clean Subspaces in VAEs

Repairing Systematic Outliers by Learning Clean Subspaces in VAEs

17 Jul 2022arXiv:2207.08050archive 2025-07-28

Simao Eduardo, Kai Xu, Alfredo Nazabal, Charles Sutton

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.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples: 19 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 20: 16 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 15 ran (6 with no instrument failure; 9 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

sfme/clsvae-error-repair officialmentioned on GitHubpytorchSyntology: 19 samples, 15 ran (9 instrument-failed) · 4 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

20 samples harvested: 16 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
9ran · our draft was wrong
1ran; the contract check could not run
5ran
4unverified

Licence: 1 of the 20 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from sfme/clsvae-error-repair. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

sfme/clsvae-error-repair official repository 19 samples, 15 ran (9 instrument-failed) · 4 unverified
BernoulliDistModule src/repair_syserr_models/semi_y_CLSVAE.py ran MIT (permissive) · 8481946e737c208b · report fixture: returned BernoulliDistModule · level recorded 2026-09-22
GaussDiagDistModule src/repair_syserr_models/semi_y_CLSVAE.py ran MIT (permissive) · cfb56fff21e907ec · report fixture: returned GaussDiagDistModule · level recorded 2026-09-22
baseDecoder src/repair_syserr_models/semi_y_CLSVAE.py ran fingerprinted MIT (permissive) · 531f02e64d7cb8c2 · report fixture: returned baseDecoder · level recorded 2026-09-22
baseEncoder src/repair_syserr_models/semi_y_CLSVAE.py ran MIT (permissive) · a49e297e81d9704b · report fixture: returned baseEncoder · level recorded 2026-09-22
distance_correlation src/repair_syserr_models/semi_y_CLSVAE.py ran · our draft was wrong fingerprinted MIT (permissive) · e043d45b15d6b755 · report fixture: signature x_sps:Tensor/2/float, y_sps:Tensor/2/float, squared:bool/0/bool · returned Tensor · level recorded 2026-09-22
kl_bern src/repair_syserr_models/semi_y_CLSVAE.py ran · our draft was wrong fingerprinted MIT (permissive) · 53481f45062c91b6 · report fixture: signature var_logit:Tensor/2/float, prior_logit:Tensor/2/float · returned Tensor · level recorded 2026-09-22
kl_gauss_diag src/repair_syserr_models/semi_y_CLSVAE.py ran · honoured contract MIT (permissive) · e9f356ae0089c419 · report fixture: signature var_params:dict/0/?, prior_params:dict/0/? · returned Tensor · level recorded 2026-09-22
logit_fn src/repair_syserr_models/semi_y_CLSVAE.py ran · our draft was wrong fingerprinted MIT (permissive) · 5dad1c9bfeeba510 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
masker src/repair_syserr_models/semi_y_CLSVAE.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · f44725a1fe393af6 · report fixture: signature logit_pi:Tensor/2/float, gs_temp:float/0/float, stochastic:bool/0/bool, dropout:bool/0/bool, out_shape:list/1/int · returned Tensor · level recorded 2026-09-22
merge_leading_dims src/repair_syserr_models/semi_y_CLSVAE.py ran · our draft was wrong fingerprinted MIT (permissive) · b6cc480db383d7f8 · report fixture: signature x:Tensor/4/float, num_dims:int/0/int · returned Tensor · level recorded 2026-09-22
modSeq src/repair_syserr_models/semi_y_CLSVAE.py ran fingerprinted MIT (permissive) · 015859f1f739f8d4 · report fixture: returned modSeq · level recorded 2026-09-22
nll_binary_global src/repair_syserr_models/semi_y_CLSVAE.py ran · our draft was wrong fingerprinted MIT (permissive) · 8f191236fc907a34 · report fixture: signature logit_p:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded 2026-09-22
nll_categ_global src/repair_syserr_models/semi_y_CLSVAE.py ran · our draft was wrong MIT (permissive) · d4257574f5fb26e9 · report fixture: signature categ_logp_feat:Tensor/2/float, input_idx_feat:Tensor/1/int · returned Tensor · level recorded 2026-09-22
nll_gauss_global src/repair_syserr_models/semi_y_CLSVAE.py ran · our draft was wrong MIT (permissive) · 494226cd33056112 · report fixture: signature gauss_params:Tensor/1/float, input_val_feat:Tensor/1/float, logvar:Tensor/2/float, shape_feats:list/1/int · returned Tensor · level recorded 2026-09-22
repeat_rows src/repair_syserr_models/semi_y_CLSVAE.py ran · our draft was wrong fingerprinted MIT (permissive) · 82ebdfc64ea97bb7 · report fixture: signature x:Tensor/3/float, num_reps:int/0/int, collapse:bool/0/bool · returned Tensor · level recorded 2026-09-22
VAE in 29 papers src/repair_syserr_models/semi_y_CLSVAE.py unverified MIT (permissive) · 7b62da118d40ebcf · report
nll_batch_noreduce src/repair_syserr_models/semi_y_CLSVAE.py unverified MIT (permissive) · 4084058cfba14167 · report
semi_y_vae_partitioned_ELBO src/repair_syserr_models/semi_y_CLSVAE.py unverified MIT (permissive) · 93debe3df0d62ace · report
y_weighted_nll src/repair_syserr_models/semi_y_CLSVAE.py unverified MIT (permissive) · ecb04549beebc113 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
split_leading_dim repository not located ran · our draft was wrong licence of this copy not recorded · a27183852b672b4c · report fixture: signature x:Tensor/2/float, shape:tuple/1/int · returned Tensor · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Clean Subspace Variational Autoencoder (CLSVAE) (graph method: Clean Subspace Variational Autoencoder (CLSVAE)). 20 bricks; individually on a fixture: 16 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 10 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. VAE entry · level 0 · unverified · 7b62da118d40ebcf
  2. BernoulliDistModule helper · level 1 · ran · 8481946e737c208b
  3. GaussDiagDistModule helper · level 1 · ran · cfb56fff21e907ec
  4. baseDecoder helper · level 1 · ran · 531f02e64d7cb8c2
  5. baseEncoder helper · level 1 · ran · a49e297e81d9704b
  6. modSeq helper · level 1 · ran · 015859f1f739f8d4
  7. semi_y_vae_partitioned_ELBO helper · level 0 · unverified · 93debe3df0d62ace
  8. logit_fn helper · level 1 · ran · our draft was wrong · 5dad1c9bfeeba510
  9. repeat_rows helper · level 1 · ran · our draft was wrong · 82ebdfc64ea97bb7
  10. split_leading_dim helper · level 1 · ran · our draft was wrong · a27183852b672b4c
  11. masker helper · level 1 · ran; the contract check could not run (RAISES) · f44725a1fe393af6
  12. distance_correlation helper · level 1 · ran · our draft was wrong · e043d45b15d6b755
  13. kl_bern helper · level 1 · ran · our draft was wrong · 53481f45062c91b6
  14. kl_gauss_diag helper · level 1 · ran · honoured contract · e9f356ae0089c419
  15. y_weighted_nll helper · level 0 · unverified · ecb04549beebc113
  16. merge_leading_dims helper · level 1 · ran · our draft was wrong · b6cc480db383d7f8
  17. nll_batch_noreduce helper · level 0 · unverified · 4084058cfba14167
  18. nll_binary_global helper · level 1 · ran · our draft was wrong · 8f191236fc907a34
  19. nll_categ_global helper · level 1 · ran · our draft was wrong · d4257574f5fb26e9
  20. nll_gauss_global helper · level 1 · ran · our draft was wrong · 494226cd33056112

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2207.08050") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Outlier Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Repair

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections