Papers › Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer

Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizer

19 Jul 2018ICLR 2019 5arXiv:1807.07543archive 2025-07-28

David Berthelot, Colin Raffel, Aurko Roy, Ian Goodfellow

Autoencoders provide a powerful framework for learning compressed representations by encoding all of the information needed to reconstruct a data point in a latent code. In some cases, autoencoders can "interpolate": By decoding the convex combination of the latent codes for two datapoints, the autoencoder can produce an output which semantically mixes characteristics from the datapoints. In this paper, we propose a regularization procedure which encourages interpolated outputs to appear more realistic by fooling a critic network which has been trained to recover the mixing coefficient from interpolated data. We then develop a simple benchmark task where we can quantitatively measure the extent to which various autoencoders can interpolate and show that our regularizer dramatically improves interpolation in this setting. We also demonstrate empirically that our regularizer produces latent codes which are more effective on downstream tasks, suggesting a possible link between interpolation abilities and learning useful representations.

PaperPDFConference PDFCodeCode Syntology ran

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 3 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 10 samples from 2 repositories, 9 ran (3 with no instrument failure; 6 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

brain-research/acai officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: not harvested report
anonymous-iclr-2019/acai-iclr-2019 officialmentioned in papertfApache-2.0Syntology: 4 samples, 2 ran (0 instrument-failed) · 2 unverified report
baohq1595/aae-experiment mentioned on GitHubtfSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
dariocazzani/pytorch-ae mentioned on GitHubpytorchSyntology: not harvested report
greentfrapp/acai-berry mentioned on GitHubtfSyntology: not harvested report
ivanvovk/controllable-face-generation mentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (4 instrument-failed) · 1 unverified report
sidwa/ae_thesis mentioned on GitHubpytorchSyntology: not harvested 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: 11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; 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
4ran · our draft was wrong
2ran; the contract check could not run
3ran
3unverified

Licence: 5 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 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. 2 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another 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”. “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.

anonymous-iclr-2019/acai-iclr-2019 official repository 4 samples, 2 ran (0 instrument-failed) · 2 unverified
draw_line in 8 papers lib/data.py ran Apache-2.0 (permissive) · d1676a94e8a860db · report fixture: signature angle:float/0/float, height:int/0/int, width:int/0/int, w:float/0/float · returned ndarray · level recorded 2026-09-25
input_lines lib/data.py ran Apache-2.0 (permissive) · d920996d38490ef5 · report fixture: signature batch_size:int/0/int, size:tuple/1/int, limit:int/0/int · returned tuple · level recorded 2026-09-25
get_latents_and_labels cluster.py unverified Apache-2.0 (permissive) · 9d0f581182913f69 · report
single_layer_classifier lib/classifiers.py unverified Apache-2.0 (permissive) · 0f185dd0ad0c3ed4 · report
baohq1595/aae-experiment community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
avg_losses src/model/mnist_aae.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 3d2866ba4046ca98 · report fixture: signature total_losses:list/1/dict · returned dict · level recorded 2026-09-22
make_image_grid in 9 papers src/model/mnist_aae.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran; the contract check could not run (RAISES) · metamorphic tier: well formed licence of this copy not recorded · 73a2b3dfb83b794b · report fixture: signature imgs:list/1/ndarray, shape:tuple/1/int, prefix:str/0/str, save_path:str/0/str, is_show:bool/0/bool · returned PngImageFile · level recorded 2026-09-22
ivanvovk/controllable-face-generation community (archive-listed) 8 samples, 7 ran (4 instrument-failed) · 1 unverified
is_sequence in 10 papers lreq.py ran · violated contract fingerprinted MIT (permissive) here; the stored copy is pointer only · eb766ff11551476d · report fixture: signature arg:list/1/int · returned bool · level recorded 2026-09-22
kl in 20 papers losses.py ran · our draft was wrong fingerprinted MIT (permissive) · 96e5a2bdc93b101d · report fixture: signature mu:Tensor/2/float, log_var:Tensor/2/float · returned Tensor · level recorded 2026-09-24
make_tuple in 11 papers lreq.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 509d9bfd9a1c5420 · report fixture: signature x:int/0/int, n:int/0/int · returned tuple · level recorded 2026-09-22
pixel_norm in 13 papers modules.py ran · our draft was wrong fingerprinted MIT (permissive) · a320e6151da0b774 · report fixture: signature x:Tensor/2/float, epsilon:float/0/float · returned Tensor · level recorded 2026-09-24
reconstruction in 10 papers losses.py ran · our draft was wrong fingerprinted MIT (permissive) · d1629b5dc1a4aac0 · report fixture: signature recon_x:Tensor/2/float, x:Tensor/2/float, lod:NoneType/0/? · returned Tensor · level recorded 2026-09-24
style_mod in 7 papers modules.py ran MIT (permissive) · 01cc5106835be4f8 · report fixture: signature x:Tensor/4/float, style:Tensor/2/float · returned Tensor · level recorded 2026-09-26
upscale2d in 10 papers modules.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) here; the stored copy is pointer only · 10f278fd8f76579c · report fixture: signature x:Tensor/4/float, factor:int/0/int · returned Tensor · level recorded 2026-09-22
discriminator_logistic_simple_gp in 6 papers losses.py unverified MIT (permissive) · 2d1d3999674791df · report

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