Papers › Realistic Evaluation of Deep Semi-Supervised Learning Algorithms

Realistic Evaluation of Deep Semi-Supervised Learning Algorithms

24 Apr 2018NeurIPS 2018 12arXiv:1804.09170archive 2025-07-28

Avital Oliver, Augustus Odena, Colin Raffel, Ekin D. Cubuk, Ian J. Goodfellow

Semi-supervised learning (SSL) provides a powerful framework for leveraging unlabeled data when labels are limited or expensive to obtain. SSL algorithms based on deep neural networks have recently proven successful on standard benchmark tasks. However, we argue that these benchmarks fail to address many issues that these algorithms would face in real-world applications. After creating a unified reimplementation of various widely-used SSL techniques, we test them in a suite of experiments designed to address these issues. We find that the performance of simple baselines which do not use unlabeled data is often underreported, that SSL methods differ in sensitivity to the amount of labeled and unlabeled data, and that performance can degrade substantially when the unlabeled dataset contains out-of-class examples. To help guide SSL research towards real-world applicability, we make our unified reimplemention and evaluation platform publicly available.

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 15 code samples harvested from 5 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 1 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: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 14 samples from 4 repositories, 8 ran (6 with no instrument failure; 2 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. 1 of the 9 samples that ran has no recorded date.

brain-research/realistic-ssl-evaluation officialmentioned in papermentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
DavidKo3/semi_supervised_mean_teacher mentioned on GitHubpytorchSyntology: 3 samples, 0 ran · 3 unverified report
layumi/SOTA-semi mentioned on GitHubSyntology: not harvested report
melkherj/puddle mentioned on GitHubMITSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
perrying/realistic-ssl-evaluation-pytorch mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
siit-vtt/semi-supervised-learning-pytorch mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
siit-vtt/ssl mentioned on GitHubpytorchMITSyntology: 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

15 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 6 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 · honoured contract
1ran · our draft was wrong
2ran; the contract check could not run
5ran
6unverified

Licence: 2 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 5 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. “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.

brain-research/realistic-ssl-evaluation official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
top_k in 17 papers
census: 7 implementations from 9 papers, 5 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
evaluate_model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 4c46154099e4d408 · report fixture: signature logits:ndarray/2/float, k:int/0/int · returned ndarray · level recorded 2026-09-22
DavidKo3/semi_supervised_mean_teacher community (archive-listed) 3 samples, 0 ran · 3 unverified
train_mt methods.py unverified MIT (permissive) · ae84d93c214dfa6a · report
train_pi methods.py unverified MIT (permissive) · 2250115852053551 · report
train_sup methods.py unverified MIT (permissive) · 915404fc2dd8ffd9 · report
melkherj/puddle community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
active_evaluate puddle/active_evaluate.py ran MIT (permissive) · fefabd373ecadbc2 · report fixture: signature X:ndarray/2/float, Y:ndarray/1/bool, model:LogisticRegression/0/?, selector:SimpleSelector/0/?, epochs:int/0/int, labels_per_epoch:int/0/int, bootstrap_size:int/0/int, batch_run:int/0/int, batch_info:str/0/str · returned DataFrame · level recorded 2026-09-26
bert_featurize puddle/datasets/amazon_reviews_bert.py ran MIT (permissive) · 436b1dc12d590080 · report fixture: signature txt:str/0/str, bert_model:callable/0/?, bert_tokenizer:MockTokenizer/0/? · returned Tensor · level recorded 2026-09-26
run_experiment in 22 papers puddle/active_evaluate.py ran MIT (permissive) · 4f47977b925bb5e5 · report fixture: signature experiment:tuple/1/tuple, epochs:int/0/int, labels_per_epoch:int/0/int · returned DataFrame · level recorded 2026-09-26
binary_class_metrics puddle/active_evaluate.py unverified MIT (permissive) · 05c1950f5c932d08 · report
sklearn_binarize_by_percentile puddle/datasets/sklearn_datasets.py unverified MIT (permissive) · d035fc4df55fe056 · report
perrying/realistic-ssl-evaluation-pytorch community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
get_zca_normalization_param build_dataset.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted MIT (permissive) · 1f390b46a93ced80 · report fixture: signature images:ndarray/4/float, scale:float/0/float, eps:float/0/float · returned tuple · level recorded 2026-09-22
gcn in 7 papers build_dataset.py unverified MIT (permissive) · 20ec0d4caa9c361d · report
siit-vtt/semi-supervised-learning-pytorch community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
check_size loader_cifar_zca.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 9570e36a7f52ab5d · report fixture: signature size:int/0/int · returned tuple · level recorded 2026-09-22
conv3x3 in 1,376 papers preresnet_sd_cifar.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
horizontal_flip in 12 papers loader_cifar_zca.py ran fingerprinted MIT (permissive) · b96d4224eb3255fa · report fixture: signature image:ndarray/3/int, rate:float/0/float · returned ndarray · level recorded 2026-09-26
random_crop in 59 papers loader_cifar_zca.py ran fingerprinted MIT (permissive) · 55f1499fcb95cc00 · report fixture: signature image:ndarray/3/int, crop_size:int/0/int, padding:int/0/int · returned ndarray · level recorded 2026-09-26

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