Papers › Adversarial Autoencoders

Adversarial Autoencoders

18 Nov 2015arXiv:1511.05644archive 2025-07-28

Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, Ian Goodfellow, Brendan Frey

In this paper, we propose the "adversarial autoencoder" (AAE), which is a probabilistic autoencoder that uses the recently proposed generative adversarial networks (GAN) to perform variational inference by matching the aggregated posterior of the hidden code vector of the autoencoder with an arbitrary prior distribution. Matching the aggregated posterior to the prior ensures that generating from any part of prior space results in meaningful samples. As a result, the decoder of the adversarial autoencoder learns a deep generative model that maps the imposed prior to the data distribution. We show how the adversarial autoencoder can be used in applications such as semi-supervised classification, disentangling style and content of images, unsupervised clustering, dimensionality reduction and data visualization. We performed experiments on MNIST, Street View House Numbers and Toronto Face datasets and show that adversarial autoencoders achieve competitive results in generative modeling and semi-supervised classification tasks.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1511.05644")

Code

Syntology Ran 8 of 12 code samples harvested from 7 repositories linked to this paper; 4 have no recorded run. Of those that ran: 3 ran · honoured contract; 1 ran · violated contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 12 samples from 7 repositories, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

29 repositories listed; official and paper-mentioned ones first.

Aiden-Jeon/AdversarialAutoencoder mentioned on GitHubpytorch report
Andrea-V/MusAE mentioned on GitHubtfMIT report
Gauravshahare/ADVERSIAL_AUTOENCODER mentioned on GitHubpytorch report
anonyme20/nips20 mentioned on GitHub report
baohq1595/aae-experiment mentioned on GitHubtf report
clementchadebec/benchmark_VAE mentioned on GitHubpytorch report
eriklindernoren/Keras-GAN mentioned on GitHubpytorch report
eriklindernoren/PyTorch-GAN mentioned on GitHubpytorch report
g4vrel/AAE mentioned on GitHubpytorch report
greentfrapp/adversarialautoencoder mentioned on GitHubtfMIT report
greentfrapp/keras-aae mentioned on GitHub report
hwalsuklee/tensorflow-mnist-AAE mentioned on GitHubtf report
jos139/adversarial_autoencoder mentioned on GitHubpytorch report
jprost76/AAE-Pytorch mentioned on GitHubpytorch report
lvyufeng/MindSpore-GAN mentioned on GitHubmindsporeMIT report
oadonca/ANVAE mentioned on GitHubtfMIT report
qq456cvb/AAE mentioned on GitHubtf report
santi-pdp/pase mentioned on GitHubpytorch report
selimseker/logogram-language-generator mentioned on GitHubpytorch report
vitskvara/GenModels.jl mentioned on GitHub report
zcemycl/Matlab-GAN mentioned on GitHubpytorchMIT report
zzmtsvv/adversarial mentioned on GitHubpytorch 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

12 samples harvested; 8 ran; 3 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
1ran · fixture could not drive it
4unverified

Licence: 9 of the 12 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 7 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

avg_losses baohq1595/aae-experiment/src/model/mnist_aae.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 3d2866ba4046ca98 · report
check_args hwalsuklee/tensorflow-mnist-AAE/run_main.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · c7ed80691a368de3 · report
gaussian_mixture jos139/adversarial_autoencoder/aae.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 26a630db1914721f · report
inv jos139/adversarial_autoencoder/aae.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 64252dfe2a75885d · report
make_image_grid baohq1595/aae-experiment/src/model/mnist_aae.py community (archive-listed) ran · fixture could not drive it no licence file found · pointer only · 73a2b3dfb83b794b · report
preprocess_im conan7882/adversarial-autoencoders/experiment/aae_mnist.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · 152ba4ed32237f48 · report
swiss_roll jos139/adversarial_autoencoder/aae.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 4f0ab02e64f2ec0d · report
vectors_to_images jprost76/AAE-Pytorch/train1.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 20789cb01b3f4b7d · report
fake_target jprost76/AAE-Pytorch/train1.py community (archive-listed) unverified no licence file found · pointer only · 0abb287af2dc9eb5 · report
real_target jprost76/AAE-Pytorch/train1.py community (archive-listed) unverified no licence file found · pointer only · 0f3cc62685e2a417 · report
reparameterization eriklindernoren/PyTorch-GAN/implementations/aae/aae.py community (archive-listed) unverified MIT (permissive) · 2adb980085821137 · report
shuffle greentfrapp/adversarialautoencoder/anomaly_detectors.py community (archive-listed) unverified MIT (permissive) · 145208e8e4762951 · report

Tasks

ClusteringData VisualizationDecoderDimensionality ReductionGeneral ClassificationUnsupervised Image ClassificationUnsupervised MNISTVariational Inference

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Image Classification MNIST Adversarial AE Accuracy 95.9 #7 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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