Papers › Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation

Exemplar VAE: Linking Generative Models, Nearest Neighbor Retrieval, and Data Augmentation

9 Apr 2020NeurIPS 2020 12arXiv:2004.04795archive 2025-07-28

Sajad Norouzi, David J. Fleet, Mohammad Norouzi

We introduce Exemplar VAEs, a family of generative models that bridge the gap between parametric and non-parametric, exemplar based generative models. Exemplar VAE is a variant of VAE with a non-parametric prior in the latent space based on a Parzen window estimator. To sample from it, one first draws a random exemplar from a training set, then stochastically transforms that exemplar into a latent code and a new observation. We propose retrieval augmented training (RAT) as a way to speed up Exemplar VAE training by using approximate nearest neighbor search in the latent space to define a lower bound on log marginal likelihood. To enhance generalization, model parameters are learned using exemplar leave-one-out and subsampling. Experiments demonstrate the effectiveness of Exemplar VAEs on density estimation and representation learning. Importantly, generative data augmentation using Exemplar VAEs on permutation invariant MNIST and Fashion MNIST reduces classification error from 1.17% to 0.69% and from 8.56% to 8.16%.

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 11 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 7 ran (2 with no instrument failure; 5 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 7 samples that ran has no recorded date.

sajadn/Exemplar-VAE officialmentioned in papermentioned on GitHubpytorchSyntology: 11 samples, 7 ran (5 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

11 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 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 · violated contract
5ran · our draft was wrong
1ran
4unverified

Licence: 0 of the 11 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 sajadn/Exemplar-VAE. “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”. “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.

sajadn/Exemplar-VAE official repository 11 samples, 7 ran (5 instrument-failed) · 4 unverified
NonLinear models/AbsHModel.py ran fingerprinted MIT (permissive) · 83d5efafa2e9fa3d · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
log_bernoulli models/AbsHModel.py ran · our draft was wrong fingerprinted MIT (permissive) · 47a8f94603764f4a · report fixture: signature x:Tensor/2/float, mean:Tensor/2/float, average:bool/0/bool, dim:NoneType/0/? · returned Tensor · level recorded 2026-09-22
log_logistic_256 models/AbsHModel.py ran · our draft was wrong MIT (permissive) · e1f4cbecd2690e02 · report fixture: signature x:Tensor/2/float, mean:Tensor/2/float, logvar:Tensor/2/float, average:bool/0/bool, reduce:bool/0/bool, dim:NoneType/0/? · returned Tensor · level recorded 2026-09-24
log_normal_diag in 5 papers models/AbsHModel.py ran · our draft was wrong fingerprinted MIT (permissive) · 731dd232f4b8579f · report fixture: signature x:Tensor/2/float, mean:Tensor/2/float, log_var:Tensor/2/float, average:bool/0/bool, dim:NoneType/0/? · returned Tensor · level recorded 2026-09-22
log_normal_standard models/AbsHModel.py ran · our draft was wrong fingerprinted MIT (permissive) · 3efb45c64b1acc4f · report fixture: signature x:Tensor/2/float, average:bool/0/bool, dim:NoneType/0/? · returned Tensor · level recorded 2026-09-22
pairwise_distance in 55 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
models/AbsHModel.py ran · our draft was wrong fingerprinted MIT (permissive) · 6ed5264974435fff · report fixture: signature z:Tensor/2/float, means:Tensor/2/float · returned Tensor · level recorded 2026-09-22
str2bool in 533 papers density_estimation.py ran · violated contract MIT (permissive) · 7c508037b40522af · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
BaseHModel models/AbsHModel.py unverified MIT (permissive) · be1641f21e463020 · report
BaseModel in 92 papers models/AbsHModel.py unverified MIT (permissive) · cc1a45d6071c9a68 · report
log_normal_diag_vectorized models/AbsHModel.py unverified MIT (permissive) · 2d62e9d56869c173 · report
normal_init in 11 papers models/AbsHModel.py unverified MIT (permissive) · 62618079bb543102 · 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.

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

harvested Assembly for Exemplar VAE (graph method: Exemplar VAE). 11 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. BaseHModel entry · level 0 · unverified · be1641f21e463020
  2. BaseModel helper · level 0 · unverified · cc1a45d6071c9a68
  3. log_normal_diag helper · level 1 · ran · our draft was wrong · 731dd232f4b8579f
  4. NonLinear helper · level 1 · ran · 83d5efafa2e9fa3d
  5. he_init helper · level 0 · unverified · a61c21baef53a292
  6. log_bernoulli helper · level 1 · ran · our draft was wrong · 47a8f94603764f4a
  7. log_logistic_256 helper · level 1 · ran · our draft was wrong · e1f4cbecd2690e02
  8. log_normal_diag_vectorized helper · level 0 · unverified · 2d62e9d56869c173
  9. log_normal_standard helper · level 1 · ran · our draft was wrong · 3efb45c64b1acc4f
  10. normal_init helper · level 0 · unverified · 62618079bb543102
  11. pairwise_distance helper · level 1 · ran · our draft was wrong · 6ed5264974435fff

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="2004.04795") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationDensity EstimationRepresentation LearningRetrievalVariational Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SPEED

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