Papers › Combating Representation Learning Disparity with Geometric Harmonization

Combating Representation Learning Disparity with Geometric Harmonization

26 Oct 2023NeurIPS 2023 11arXiv:2310.17622archive 2025-07-28

Zhihan Zhou, Jiangchao Yao, Feng Hong, Ya zhang, Bo Han, Yanfeng Wang

Self-supervised learning (SSL) as an effective paradigm of representation learning has achieved tremendous success on various curated datasets in diverse scenarios. Nevertheless, when facing the long-tailed distribution in real-world applications, it is still hard for existing methods to capture transferable and robust representation. Conventional SSL methods, pursuing sample-level uniformity, easily leads to representation learning disparity where head classes dominate the feature regime but tail classes passively collapse. To address this problem, we propose a novel Geometric Harmonization (GH) method to encourage category-level uniformity in representation learning, which is more benign to the minority and almost does not hurt the majority under long-tailed distribution. Specially, GH measures the population statistics of the embedding space on top of self-supervised learning, and then infer an fine-grained instance-wise calibration to constrain the space expansion of head classes and avoid the passive collapse of tail classes. Our proposal does not alter the setting of SSL and can be easily integrated into existing methods in a low-cost manner. Extensive results on a range of benchmark datasets show the effectiveness of GH with high tolerance to the distribution skewness. Our code is available at https://github.com/MediaBrain-SJTU/Geometric-Harmonization.

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 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 12 ran (6 with no instrument failure; 6 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 12 samples that ran have no recorded date.

MediaBrain-SJTU/Geometric-Harmonization officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 12 ran (6 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

15 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 6 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.

1ran · violated contract
6ran · our draft was wrong
5ran
3unverified

Licence: 4 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 MediaBrain-SJTU/Geometric-Harmonization. “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.

MediaBrain-SJTU/Geometric-Harmonization official repository 15 samples, 12 ran (6 instrument-failed) · 3 unverified
ResNet18 in 174 papers resnet.py ran MIT (permissive) · 43a1d3b25104ae7a · report fixture: signature low_dim:int/0/int, use_norm:bool/0/bool · returned ResNet · level recorded 2026-09-24
ResNet34 in 91 papers resnet.py ran MIT (permissive) · c2b0a60d47724297 · report fixture: signature low_dim:int/0/int, use_norm:bool/0/bool · returned ResNet · level recorded 2026-09-24
ShearX in 14 papers BCL/randaug.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 9846307204b08173 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
ShearY in 14 papers BCL/randaug.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 109155544d6d2c48 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
TranslateX in 13 papers BCL/randaug.py ran · our draft was wrong MIT (permissive) · f03d112eee854337 · report fixture: signature img:Image/0/?, v:float/0/float · returned Image · level recorded 2026-09-22
conv1x1 in 691 papers resnet_imagenet.py ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv1x1 in 691 papers SDCLR/resnet_prune.py ran MIT (permissive) · 1cd86864f32ad467 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned prune_conv2d · level recorded 2026-09-24
conv3x3 in 1,376 papers resnet_imagenet.py ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers SDCLR/resnet_prune.py ran MIT (permissive) · ae216d6807b93383 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned prune_conv2d · level recorded 2026-09-24
get_negative_mask in 6 papers utils.py ran · violated contract MIT (permissive) here; the stored copy is pointer only · b09a2cc2e21f2012 · report fixture: signature batch_size:int/0/int · returned Tensor · level recorded 2026-09-25
normalize_fn in 11 papers resnet.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 0e0f66ffb7a61530 · report fixture: signature tensor:Tensor/4/float, mean:Tensor/1/float, std:Tensor/1/float · returned Tensor · level recorded 2026-09-24
sinkhorn in 47 papers
census: 11 implementations from 11 papers, 11 distinct outputs across 2 buckets, one shared input per bucket
utils.py ran MIT (permissive) · 38b1cfaaa3fc1906 · report fixture: signature out:Tensor/2/float, l:float/0/float, sinkhorn_iterations:int/0/int, stat:Tensor/1/float · returned Tensor · level recorded 2026-09-24
calculate_momentum_weight BCL/memoboosted_LT_Dataset.py unverified MIT (permissive) · 21004f703e266a6c · report
calculate_momentum_weight BCL/memoboosted_cifar100.py unverified MIT (permissive) · 01e541288a411510 · report
nt_xent in 10 papers utils.py unverified MIT (permissive) · 1223e88b708e9e08 · report

Tasks

Representation LearningSelf-Supervised 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