Papers › ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring

21 Nov 2019arXiv:1911.09785archive 2025-07-28

David Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, Colin Raffel

We improve the recently-proposed "MixMatch" semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring. Distribution alignment encourages the marginal distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels. Augmentation anchoring feeds multiple strongly augmented versions of an input into the model and encourages each output to be close to the prediction for a weakly-augmented version of the same input. To produce strong augmentations, we propose a variant of AutoAugment which learns the augmentation policy while the model is being trained. Our new algorithm, dubbed ReMixMatch, is significantly more data-efficient than prior work, requiring between 5× and 16× less data to reach the same accuracy. For example, on CIFAR-10 with 250 labeled examples we reach 93.73% accuracy (compared to MixMatch's accuracy of 93.58% with 4,000 examples) and a median accuracy of 84.92% with just four labels per class. We make our code and data open-source at https://github.com/google-research/remixmatch.

PaperPDFCodeCode 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 4 code samples: 3 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 4: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); 1 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.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

No date is recorded for the sample that ran: its level was written before Syntology's graph kept the date.

google-research/remixmatch officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Clustering by Maximizing Mutual Information Across Views (arXiv:2107.11635; that paper's own run record: 0 ran · 3 unverified); nothing checks that they implement this paper's method. report
google-research/mixmatch officialmentioned in papertfApache-2.0Syntology: 3 samples, 0 ran · 3 unverified report
zysymu/AdaMatch-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation (arXiv:2106.04732; that paper's own run record: 15 ran (of which 5 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

4 samples harvested: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure 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
3unverified

Licence: 1 of the 4 samples is 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 google-research/mixmatch. 1 sample is listed last, in a group without a repository. “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.

google-research/mixmatch official repository 3 samples, 0 ran · 3 unverified
entropy_from_logits in 13 papers libml/layers.py unverified Apache-2.0 (permissive) · 0802d913d5d3694d · report
entropy_penalty in 7 papers libml/layers.py unverified Apache-2.0 (permissive) · d5592d7541ebcb31 · report
smart_shape in 7 papers libml/layers.py unverified Apache-2.0 (permissive) · 5d8684fa279a5f80 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
summary_dict repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 043a02598e0288df · report fixture: signature accuracies:ndarray/1/float · returned dict · level recorded, date not recorded

Tasks

Image ClassificationSemi-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification STL-10 ReMixMatch (K=4) Percentage correct 93.82 #24 of 117 Archive leaderboard report
Image Classification STL-10 ReMixMatch (K=1) Percentage correct 93.23 #26 of 117 Archive leaderboard report
Image Classification STL-10 MixMatch Percentage correct 89.82 #36 of 117 Archive leaderboard report
Image Classification STL-10 CC-GAN Percentage correct 77.80 #70 of 117 Archive leaderboard report
Image Classification STL-10 SWWAE Percentage correct 74.30 #78 of 117 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 250 Labels ReMixMatch Percentage error 6.27 #19 of 27 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 40 Labels ReMixMatch Percentage error 19.10 #21 of 21 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-10, 4000 Labels ReMixMatch Percentage error 5.14 #24 of 49 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-100, 2500 Labels ReMixMatch Percentage error 27.43±0.31 #14 of 16 Archive leaderboard report
Semi-Supervised Image Classification CIFAR-100, 400 Labels ReMixMatch Percentage error 44.28±2.06 #17 of 21 Archive leaderboard report
Semi-Supervised Image Classification STL-10, 1000 Labels ReMixMatch Accuracy 93.82 #8 of 13 Archive leaderboard report
Semi-Supervised Image Classification SVHN, 1000 labels ReMixMatch Accuracy 97.17 #6 of 17 Archive leaderboard report
Semi-Supervised Image Classification cifar10, 250 Labels ReMixMatch Percentage correct 93.73 #1 of 4 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.

Methods

AutoAugmentLSTMSigmoid ActivationTanh Activation

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