Papers › Early-Learning Regularization Prevents Memorization of Noisy Labels

Early-Learning Regularization Prevents Memorization of Noisy Labels

30 Jun 2020NeurIPS 2020 12arXiv:2007.00151archive 2025-07-28

Sheng Liu, Jonathan Niles-Weed, Narges Razavian, Carlos Fernandez-Granda

We propose a novel framework to perform classification via deep learning in the presence of noisy annotations. When trained on noisy labels, deep neural networks have been observed to first fit the training data with clean labels during an "early learning" phase, before eventually memorizing the examples with false labels. We prove that early learning and memorization are fundamental phenomena in high-dimensional classification tasks, even in simple linear models, and give a theoretical explanation in this setting. Motivated by these findings, we develop a new technique for noisy classification tasks, which exploits the progress of the early learning phase. In contrast with existing approaches, which use the model output during early learning to detect the examples with clean labels, and either ignore or attempt to correct the false labels, we take a different route and instead capitalize on early learning via regularization. There are two key elements to our approach. First, we leverage semi-supervised learning techniques to produce target probabilities based on the model outputs. Second, we design a regularization term that steers the model towards these targets, implicitly preventing memorization of the false labels. The resulting framework is shown to provide robustness to noisy annotations on several standard benchmarks and real-world datasets, where it achieves results comparable to the state of the art.

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 1 code sample harvested from 1 repository linked to this paper: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

shengliu66/ELR officialmentioned in papermentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
shengliu66/sop mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Robust Training under Label Noise by Over-parameterization (arXiv:2202.14026; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 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

1 sample harvested: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 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 · violated contract

Licence: 0 of the 1 sample 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 shengliu66/ELR. “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.

shengliu66/ELR official repository 1 sample, 1 ran (0 instrument-failed) · 0 unverified
cross_entropy in 92 papers
census: 6 implementations from 8 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
ELR/model/loss.py ran · violated contract MIT (permissive) · ab1c43d5635c2cf0 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int · returned Tensor · level recorded 2026-09-22

Tasks

General ClassificationImage ClassificationLearning with noisy labelsMemorization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification Clothing1M ELR+ Accuracy 74.81% #14 of 51 Archive leaderboard report
Image Classification mini WebVision 1.0 ELR+ (Inception-ResNet-v2) ImageNet Top-1 Accuracy 70.29 #25 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 ELR+ (Inception-ResNet-v2) ImageNet Top-5 Accuracy 89.76 #25 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 ELR+ (Inception-ResNet-v2) Top-1 Accuracy 77.78 #25 of 47 Archive leaderboard report
Image Classification mini WebVision 1.0 ELR+ (Inception-ResNet-v2) Top-5 Accuracy 91.68 #25 of 47 Archive leaderboard report
Learning with noisy labels CIFAR-100N ELR+ Accuracy (mean) 66.72 #6 of 24 Archive leaderboard report
Learning with noisy labels CIFAR-100N ELR Accuracy (mean) 58.94 #12 of 24 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Aggregate ELR+ Accuracy (mean) 94.83 #8 of 26 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Aggregate ELR Accuracy (mean) 92.38 #11 of 26 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random1 ELR+ Accuracy (mean) 94.43 #7 of 24 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random1 ELR Accuracy (mean) 91.46 #9 of 24 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random2 ELR+ Accuracy (mean) 94.20 #5 of 23 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random2 ELR Accuracy (mean) 91.61 #6 of 23 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random3 ELR+ Accuracy (mean) 94.34 #5 of 23 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Random3 ELR Accuracy (mean) 91.41 #7 of 23 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Worst ELR+ Accuracy (mean) 91.09 #8 of 25 Archive leaderboard report
Learning with noisy labels CIFAR-10N-Worst ELR Accuracy (mean) 83.58 #13 of 25 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

Introduced by this paper: ELR

ELR

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