Papers › Generative Modeling Helps Weak Supervision (and Vice Versa)

Generative Modeling Helps Weak Supervision (and Vice Versa)

22 Mar 2022arXiv:2203.12023archive 2025-07-28

Benedikt Boecking, Nicholas Roberts, Willie Neiswanger, Stefano Ermon, Frederic Sala, Artur Dubrawski

Many promising applications of supervised machine learning face hurdles in the acquisition of labeled data in sufficient quantity and quality, creating an expensive bottleneck. To overcome such limitations, techniques that do not depend on ground truth labels have been studied, including weak supervision and generative modeling. While these techniques would seem to be usable in concert, improving one another, how to build an interface between them is not well-understood. In this work, we propose a model fusing programmatic weak supervision and generative adversarial networks and provide theoretical justification motivating this fusion. The proposed approach captures discrete latent variables in the data alongside the weak supervision derived label estimate. Alignment of the two allows for better modeling of sample-dependent accuracies of the weak supervision sources, improving the estimate of unobserved labels. It is the first approach to enable data augmentation through weakly supervised synthetic images and pseudolabels. Additionally, its learned latent variables can be inspected qualitatively. The model outperforms baseline weak supervision label models on a number of multiclass image classification datasets, improves the quality of generated images, and further improves end-model performance through data augmentation with synthetic samples.

PaperPDFCodeCode 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 17 code samples: 16 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 17: 12 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 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: 16 samples from 1 repository, 11 ran (9 with no instrument failure; 2 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.

benbo/wsgan-paper officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 11 ran (2 instrument-failed) · 5 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

17 samples harvested: 12 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 5 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
1ran · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
8ran
5unverified

Licence: 1 of the 17 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 benbo/wsgan-paper. 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 1 sample 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

benbo/wsgan-paper official repository 16 samples, 11 ran (2 instrument-failed) · 5 unverified
DCDiscriminatorThree lightning/module.py ran · metamorphic tier: deterministic MIT (permissive) · 6d3ca84445b61c8a · report fixture: returned DCDiscriminatorThree · level recorded 2026-09-22
DCGenerator64 lightning/module.py ran · metamorphic tier: deterministic MIT (permissive) · 805afed0b83c9d86 · report fixture: returned DCGenerator64 · level recorded 2026-09-22
DCGeneratorThree lightning/module.py ran · metamorphic tier: deterministic MIT (permissive) · 4fa1e9c8cab4c845 · report fixture: returned DCGeneratorThree · level recorded 2026-09-22
EncoderLabelmodel lightning/module.py ran · metamorphic tier: deterministic MIT (permissive) · 9a3908d102d2323b · report fixture: returned EncoderLabelmodel · level recorded 2026-09-22
InfoDCDiscriminator lightning/module.py ran · metamorphic tier: deterministic MIT (permissive) · 3eb1f0f388c9b649 · report fixture: returned InfoDCDiscriminator · level recorded 2026-09-22
InfoDCDiscriminator64 lightning/module.py ran · metamorphic tier: deterministic MIT (permissive) · 5fa6efe00c21b746 · report fixture: returned InfoDCDiscriminator64 · level recorded 2026-09-22
LinearLrSchedule lightning/module.py ran MIT (permissive) · 039df6026700e3af · report fixture: returned LinearLrSchedule · level recorded 2026-09-22
MLP in 375 papers lightning/module.py ran · metamorphic tier: deterministic MIT (permissive) · fd993e3e914b0902 · report fixture: returned MLP · level recorded 2026-09-22
_cl_update lightning/module.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 5db77e1abcabcf52 · report fixture: signature x:Tensor/1/float, y:Tensor/1/float · returned tuple · level recorded 2026-09-22
get_linear_lr_schedule lightning/module.py ran · our draft was wrong MIT (permissive) · 17ccd2118b85dd0d · report fixture: signature lr:float/0/float, n_epochs:int/0/int, minlr:float/0/float · returned method · level recorded 2026-09-22
inception_transforms lightning/module.py ran · violated contract fingerprinted MIT (permissive) · c2e3b63879be9a20 · report fixture: signature imgs:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ARI lightning/module.py unverified MIT (permissive) · 8a4ef744ac07ecc3 · report
GANLabelModel lightning/module.py unverified MIT (permissive) · b9ec6c174fb615f4 · report
InceptionScores lightning/module.py unverified MIT (permissive) · 3a35531cc71bfc4f · report
LightningGAN lightning/module.py unverified MIT (permissive) · 30d589374cf0746c · report
get_networks_base lightning/module.py unverified MIT (permissive) · 1637a6dbd0af625c · report
Repository not located 1 sample, 1 ran (0 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.
soft_cross_entropy in 25 papers
census: 6 implementations from 8 papers, 3 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
repository not located ran · honoured contract fingerprinted licence of this copy not recorded · 49e2f0c554d81ea3 · report fixture: signature pred:Tensor/2/float, soft_targets:Tensor/2/float · 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 a model fusing programmatic weak supervision and generative adversarial networks (graph method: a model fusing programmatic weak supervision and generative adversarial networks). 17 bricks; individually on a fixture: 12 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. GANLabelModel entry · level 0 · unverified · b9ec6c174fb615f4
  2. ARI helper · level 0 · unverified · 8a4ef744ac07ecc3
  3. EncoderLabelmodel helper · level 1 · ran · 9a3908d102d2323b
  4. LightningGAN helper · level 0 · unverified · 30d589374cf0746c
  5. get_linear_lr_schedule helper · level 1 · ran · our draft was wrong · 17ccd2118b85dd0d
  6. get_networks_base helper · level 0 · unverified · 1637a6dbd0af625c
  7. inception_transforms helper · level 1 · ran · violated contract · c2e3b63879be9a20
  8. soft_cross_entropy loss · level 1 · ran · honoured contract · 49e2f0c554d81ea3
  9. _cl_update helper · level 1 · ran; the contract check could not run (RAISES) · 5db77e1abcabcf52
  10. MLP helper · level 1 · ran · fd993e3e914b0902
  11. InceptionScores helper · level 0 · unverified · 3a35531cc71bfc4f
  12. LinearLrSchedule helper · level 1 · ran · 039df6026700e3af
  13. DCDiscriminatorThree model · level 1 · ran · 6d3ca84445b61c8a
  14. DCGenerator64 helper · level 1 · ran · 805afed0b83c9d86
  15. DCGeneratorThree model · level 1 · ran · 4fa1e9c8cab4c845
  16. InfoDCDiscriminator model · level 1 · ran · 3eb1f0f388c9b649
  17. InfoDCDiscriminator64 helper · level 1 · ran · 5fa6efe00c21b746

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="2203.12023") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationImage Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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