Papers › Simplifying Neural Network Training Under Class Imbalance

Simplifying Neural Network Training Under Class Imbalance

5 Dec 2023NeurIPS 2023 11arXiv:2312.02517archive 2025-07-28

Ravid Shwartz-Ziv, Micah Goldblum, Yucen Lily Li, C. Bayan Bruss, Andrew Gordon Wilson

Real-world datasets are often highly class-imbalanced, which can adversely impact the performance of deep learning models. The majority of research on training neural networks under class imbalance has focused on specialized loss functions, sampling techniques, or two-stage training procedures. Notably, we demonstrate that simply tuning existing components of standard deep learning pipelines, such as the batch size, data augmentation, optimizer, and label smoothing, can achieve state-of-the-art performance without any such specialized class imbalance methods. We also provide key prescriptions and considerations for training under class imbalance, and an understanding of why imbalance methods succeed or fail.

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 16 code samples: 14 from 1 repository linked to this paper, 2 identical to code harvested from another paper's repository. Across all 16: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 3 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 11 ran (7 with no instrument failure; 4 where Syntology's instrument failed); 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.

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. 2 of the 13 samples that ran have no recorded date.

ravidziv/simplifyingimbalancedtraining officialmentioned in paperpytorchSyntology: 14 samples, 11 ran (4 instrument-failed) · 3 unverified 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

16 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 3 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · violated contract
5ran · our draft was wrong
5ran
3unverified

Licence: 16 of the 16 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 ravidziv/simplifyingimbalancedtraining. 2 samples are 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. 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.

ravidziv/simplifyingimbalancedtraining official repository 14 samples, 11 ran (4 instrument-failed) · 3 unverified
adversarial_cross_entropy imbalanced/losses.py ran no licence file found · pointer only · e11996f54eea8253 · report fixture: signature model:callable/0/?, input:Tensor/2/float, target:Tensor/1/int, lossfn:callable/0/?, epsilon:float/0/float · returned tuple · level recorded 2026-09-24
center_crop in 48 papers imbalanced/models/layers.py ran fingerprinted no licence file found · pointer only · 9d5555c9ff725b7f · report fixture: signature layer:Tensor/4/float, max_height:int/0/int, max_width:int/0/int · returned Tensor · level recorded 2026-09-24
conv3x3 in 1,376 papers imbalanced/models/preresnet.py ran · our draft was wrong no licence file found · pointer only · 583f9780bdd00a45 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22
cross_entropy in 92 papers
census: 6 implementations from 8 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
imbalanced/losses.py ran no licence file found · pointer only · fc2aaf6fd20bc53f · report fixture: signature model:callable/0/?, input:Tensor/2/float, target:Tensor/1/int · returned tuple · level recorded 2026-09-24
get_base imbalanced/models/preresnet.py ran no licence file found · pointer only · 9ba3acf9da935ca1 · report fixture: signature num_classes:int/0/int, weights:NoneType/0/?, size:int/0/int · returned ResNet · level recorded 2026-09-24
get_resnet_transforms imbalanced/models/preresnet.py ran · our draft was wrong no licence file found · pointer only · ec01de700d8c1028 · report fixture: signature no_use_aug:bool/0/bool, size:int/0/int · returned tuple · level recorded 2026-09-24
get_sampler in 20 papers imbalanced/data.py ran · our draft was wrong no licence file found · pointer only · 3b2896cbbe245a73 · report fixture: signature dataset:SimpleDataset/0/?, weighted_training:bool/0/bool · returned WeightedRandomSampler · level recorded 2026-09-24
has_file_allowed_extension in 38 papers imbalanced/camvid.py ran · violated contract no licence file found · pointer only · 1d7c68b369e70ab0 · report fixture: signature filename:str/0/str, extensions:list/1/str · returned bool · level recorded 2026-09-24
is_image_file in 157 papers imbalanced/camvid.py ran · violated contract no licence file found · pointer only · af447e65a04b459e · report fixture: signature filename:str/0/str · returned bool · level recorded 2026-09-24
make_layers in 155 papers imbalanced/models/vgg.py ran · our draft was wrong no licence file found · pointer only · 4a29d37fffcfd8b1 · report fixture: signature cfg:list/1/int, batch_norm:bool/0/bool · returned Sequential · level recorded 2026-09-24
update_ens imbalanced/models/model_wrapper.py ran no licence file found · pointer only · ecb6936a718db4af · report fixture: signature all_preds:ndarray/2/float, sgd_ens_preds:NoneType/0/?, n_ensembled:int/0/int · returned tuple · level recorded 2026-09-24
camvid_loaders imbalanced/data.py unverified no licence file found · pointer only · e1ae5ee1960f180e · report
masked_loss in 8 papers imbalanced/losses.py unverified no licence file found · pointer only · 8bbca7799326d580 · report
svhn_loaders in 5 papers imbalanced/data.py unverified no licence file found · pointer only · ddd3f33619ad1ab9 · report
Repository not located 2 samples, 2 ran (1 instrument-failed) · 0 unverified
2 samples are 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.
get_lr in 91 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · 190117b425ab9fe1 · report fixture: signature step:int/0/int, total_steps:int/0/int, lr_max:float/0/float, lr_min:float/0/float · returned float64 · level recorded, date not recorded
nt_xent in 10 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 0931a280f76e561f · report fixture: signature x:Tensor/2/float, t:float/0/float · returned Tensor · level recorded, date not recorded

Tasks

Data AugmentationDeep Learning

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