Papers › Capturing Label Characteristics in VAEs

Capturing Label Characteristics in VAEs

17 Jun 2020ICLR 2021 1arXiv:2006.10102archive 2025-07-28

Tom Joy, Sebastian M. Schmon, Philip H. S. Torr, N. Siddharth, Tom Rainforth

We present a principled approach to incorporating labels in VAEs that captures the rich characteristic information associated with those labels. While prior work has typically conflated these by learning latent variables that directly correspond to label values, we argue this is contrary to the intended effect of supervision in VAEs-capturing rich label characteristics with the latents. For example, we may want to capture the characteristics of a face that make it look young, rather than just the age of the person. To this end, we develop the CCVAE, a novel VAE model and concomitant variational objective which captures label characteristics explicitly in the latent space, eschewing direct correspondences between label values and latents. Through judicious structuring of mappings between such characteristic latents and labels, we show that the CCVAE can effectively learn meaningful representations of the characteristics of interest across a variety of supervision schemes. In particular, we show that the CCVAE allows for more effective and more general interventions to be performed, such as smooth traversals within the characteristics for a given label, diverse conditional generation, and transferring characteristics across datapoints.

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 14 code samples harvested from 2 repositories linked to this paper: 13 ran (of which 12 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 8 samples from 1 repository, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed). 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.

thwjoy/ccvae officialmentioned in paperpytorchSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
mori97/revae mentioned on GitHubpytorchSyntology: 8 samples, 7 ran (1 instrument-failed) · 1 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

14 samples harvested: 13 ran (of which 12 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 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 · our draft was wrong
12ran
1unverified

Licence: 6 of the 14 samples are 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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 6 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. 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.

thwjoy/ccvae official repository 6 samples, 6 ran (0 instrument-failed) · 0 unverified
CELEBADecoder models/semisup_vae.py ran fingerprinted no licence file found · pointer only · 8a4777adc80a0c27 · report fixture: returned CELEBADecoder · level recorded 2026-09-22
CELEBAEncoder models/semisup_vae.py ran no licence file found · pointer only · 194a6e10b3eab0df · report fixture: returned CELEBAEncoder · level recorded 2026-09-22
Classifier in 72 papers models/semisup_vae.py ran no licence file found · pointer only · 319ead4f1c1f8df6 · report fixture: returned Classifier · level recorded 2026-09-22
CondPrior models/semisup_vae.py ran no licence file found · pointer only · b428bb64e0c11ea0 · report fixture: returned CondPrior · level recorded 2026-09-22
Diagonal models/semisup_vae.py ran no licence file found · pointer only · 3342e27354ab9e19 · report fixture: returned Diagonal · level recorded 2026-09-22
SSVAE_CCVAE models/semisup_vae.py ran no licence file found · pointer only · 9f4b467114c264bf · report fixture: returned SSVAE_CCVAE · level recorded 2026-09-22
mori97/revae community (archive-listed) 8 samples, 7 ran (1 instrument-failed) · 1 unverified
BaseREVAEMNIST models/mnist.py ran MIT (permissive) · 76a3b3ce30f40be0 · report fixture: returned BaseREVAEMNIST · level recorded 2026-09-22
REVAEMNIST models/mnist.py ran MIT (permissive) · 5a1fb6fa55266ac1 · report fixture: returned REVAEMNIST · level recorded 2026-09-22
_Classifier models/mnist.py ran fingerprinted MIT (permissive) · 50e4b27b44bab302 · report fixture: returned _Classifier · level recorded 2026-09-22
_ConditionalPrior models/mnist.py ran MIT (permissive) · 52e0ab14a73e3c8b · report fixture: returned _ConditionalPrior · level recorded 2026-09-22
_Decoder models/mnist.py ran fingerprinted MIT (permissive) · a0ca0389acc43dae · report fixture: returned _Decoder · level recorded 2026-09-22
_Encoder models/mnist.py ran MIT (permissive) · 8cc912b6c76d68f3 · report fixture: returned _Encoder · level recorded 2026-09-22
reparameterize in 38 papers
census: 12 implementations from 17 papers, 5 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
models/mnist.py ran · our draft was wrong fingerprinted MIT (permissive) · d7b93d9b79b19888 · report fixture: signature mu:Tensor/2/float, logvar:Tensor/2/float, n_samples:int/0/int · returned Tensor · level recorded 2026-09-22
_check_label models/mnist.py unverified MIT (permissive) · f0a964e499bbb150 · report

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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for CCVAE (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for CCVAE (graph method: CCVAE). 8 bricks; individually on a fixture: 7 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. REVAEMNIST entry · level 1 · ran · 5a1fb6fa55266ac1
  2. BaseREVAEMNIST helper · level 1 · ran · 76a3b3ce30f40be0
  3. _check_label helper · level 0 · unverified · f0a964e499bbb150
  4. reparameterize helper · level 1 · ran · our draft was wrong · d7b93d9b79b19888
  5. _Classifier model · level 1 · ran · 50e4b27b44bab302
  6. _ConditionalPrior model · level 1 · ran · 52e0ab14a73e3c8b
  7. _Decoder model · level 1 · ran · a0ca0389acc43dae
  8. _Encoder model · level 1 · ran · 8cc912b6c76d68f3

harvested Assembly for CCVAE (graph method: CCVAE). 7 bricks; individually on a fixture: 7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 7 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. SSVAE_CCVAE entry · level 1 · ran · 9f4b467114c264bf
  2. CELEBADecoder model · level 1 · ran · 8a4777adc80a0c27
  3. CELEBAEncoder model · level 1 · ran · 194a6e10b3eab0df
  4. Classifier model · level 1 · ran · 319ead4f1c1f8df6
  5. CondPrior model · level 1 · ran · b428bb64e0c11ea0
  6. View helper · level 1 · ran · d98e6eb646f75ed8
  7. Diagonal helper · level 1 · ran · 3342e27354ab9e19

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="2006.10102") returns these assemblies with each brick's role and wiring (how to connect).

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