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 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="1807.07543")

Code

Syntology Ran 8 of 14 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 0 ran; community (archive-listed): 8 samples from 1 repository, 6 ran; 2 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.

brain-research/acai officialmentioned in papermentioned on GitHubtfApache-2.0 report
anonymous-iclr-2019/acai-iclr-2019 officialmentioned in papertfApache-2.0 report
baohq1595/aae-experiment mentioned on GitHubtf report
dariocazzani/pytorch-ae mentioned on GitHubpytorch report
greentfrapp/acai-berry mentioned on GitHubtf report
ivanvovk/controllable-face-generation mentioned on GitHubpytorchMIT report
sidwa/ae_thesis 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

14 samples harvested; 8 ran; 1 honoured the contract we drafted; 6 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.

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
2ran · fixture could not drive it
3ran
6unverified

Licence: 2 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; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

draw_line anonymous-iclr-2019/acai-iclr-2019/lib/data.py official repository unverified Apache-2.0 (permissive) · d1676a94e8a860db · report
get_latents_and_labels anonymous-iclr-2019/acai-iclr-2019/cluster.py official repository unverified Apache-2.0 (permissive) · 9d0f581182913f69 · report
input_lines anonymous-iclr-2019/acai-iclr-2019/lib/data.py official repository unverified Apache-2.0 (permissive) · d920996d38490ef5 · report
single_layer_classifier anonymous-iclr-2019/acai-iclr-2019/lib/classifiers.py official repository unverified Apache-2.0 (permissive) · 0f185dd0ad0c3ed4 · report
is_sequence ivanvovk/controllable-face-generation/lreq.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · eb766ff11551476d · report
kl ivanvovk/controllable-face-generation/losses.py community (archive-listed) ran fingerprinted MIT (permissive) · 96e5a2bdc93b101d · report
make_tuple ivanvovk/controllable-face-generation/lreq.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 509d9bfd9a1c5420 · report
pixel_norm ivanvovk/controllable-face-generation/modules.py community (archive-listed) ran fingerprinted MIT (permissive) · a320e6151da0b774 · report
reconstruction ivanvovk/controllable-face-generation/losses.py community (archive-listed) ran fingerprinted MIT (permissive) · d1629b5dc1a4aac0 · report
upscale2d ivanvovk/controllable-face-generation/modules.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 10f278fd8f76579c · report
discriminator_logistic_simple_gp ivanvovk/controllable-face-generation/losses.py community (archive-listed) unverified MIT (permissive) · 2d1d3999674791df · report
style_mod ivanvovk/controllable-face-generation/modules.py community (archive-listed) unverified MIT (permissive) · 01cc5106835be4f8 · report
avg_losses identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 3d2866ba4046ca98 · report
make_image_grid identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · 73a2b3dfb83b794b · 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