Papers › When Does Label Smoothing Help?

When Does Label Smoothing Help?

6 Jun 2019NeurIPS 2019 12arXiv:1906.02629archive 2025-07-28

Rafael Müller, Simon Kornblith, Geoffrey Hinton

The generalization and learning speed of a multi-class neural network can often be significantly improved by using soft targets that are a weighted average of the hard targets and the uniform distribution over labels. Smoothing the labels in this way prevents the network from becoming over-confident and label smoothing has been used in many state-of-the-art models, including image classification, language translation and speech recognition. Despite its widespread use, label smoothing is still poorly understood. Here we show empirically that in addition to improving generalization, label smoothing improves model calibration which can significantly improve beam-search. However, we also observe that if a teacher network is trained with label smoothing, knowledge distillation into a student network is much less effective. To explain these observations, we visualize how label smoothing changes the representations learned by the penultimate layer of the network. We show that label smoothing encourages the representations of training examples from the same class to group in tight clusters. This results in loss of information in the logits about resemblances between instances of different classes, which is necessary for distillation, but does not hurt generalization or calibration of the model's predictions.

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 7 code samples: 6 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 7: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 6 samples from 2 repositories, 5 ran (5 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 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

ElenaRyumina/EMO-AffectNetModel mentioned on GitHubtfMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
jessefokkinga/MechanismsOfAction mentioned on GitHubpytorchSyntology: not harvested report
seominseok0429/label-smoothing-visualization-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
ensta-u2is/torch-uncertainty pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Training independent subnetworks for robust prediction (arXiv:2010.06610; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified), On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks (arXiv:2203.09168; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified) and Tailoring Mixup to Data for Calibration (arXiv:2311.01434; that paper's own run record: 6 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 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

7 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 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 · our draft was wrong
5ran
1unverified

Licence: 2 of the 7 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. 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.

ElenaRyumina/EMO-AffectNetModel community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
df_group functions/sequences.py ran MIT (permissive) · ef172d9e9018893b · report fixture: signature df:DataFrame/0/?, label_model:list/1/str · returned DataFrame · level recorded 2026-09-24
preprocess_input in 26 papers functions/utils.py ran MIT (permissive) · eee939c2db10a418 · report fixture: signature x:ndarray/4/float, data_format:str/0/str, version:int/0/int · returned ndarray · level recorded 2026-09-24
resnet_conv_block functions/get_models.py ran MIT (permissive) · 4f8026759621b1d5 · report fixture: signature input_tensor:EagerTensor/4/float, kernel_size:tuple/1/int, filters:tuple/1/int, stage:int/0/int, block:int/0/int, strides:tuple/1/int, bias:bool/0/bool · returned EagerTensor · level recorded 2026-09-24
sequences functions/sequences.py ran MIT (permissive) · 816fcd30b3119901 · report fixture: signature all_path:list/1/str, all_feature:Tensor/2/float, win:int/0/int, step:int/0/int · returned tuple · level recorded 2026-09-24
resnet_identity_block functions/get_models.py unverified MIT (permissive) · a396c058d14ded87 · report
seominseok0429/label-smoothing-visualization-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_mean_and_std in 55 papers utils.py ran · metamorphic tier: well formed no licence file found · pointer only · 3cbdd3b190b16350 · report fixture: signature dataset:MinimalDataset/0/? · returned tuple · level recorded 2026-09-22
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.
format_time in 140 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 8d7ec010c29e813b · report fixture: signature seconds:float/0/float · returned str · level recorded, date not recorded

Tasks

Image ClassificationKnowledge DistillationSpeech RecognitionTranslationimage-classificationspeech-recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Knowledge DistillationLabel SmoothingSPEED

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