Papers › LDReg: Local Dimensionality Regularized Self-Supervised Learning

LDReg: Local Dimensionality Regularized Self-Supervised Learning

19 Jan 2024arXiv:2401.10474archive 2025-07-28

Hanxun Huang, Ricardo J. G. B. Campello, Sarah Monazam Erfani, Xingjun Ma, Michael E. Houle, James Bailey

Representations learned via self-supervised learning (SSL) can be susceptible to dimensional collapse, where the learned representation subspace is of extremely low dimensionality and thus fails to represent the full data distribution and modalities. Dimensional collapse also known as the "underfilling" phenomenon is one of the major causes of degraded performance on downstream tasks. Previous work has investigated the dimensional collapse problem of SSL at a global level. In this paper, we demonstrate that representations can span over high dimensional space globally, but collapse locally. To address this, we propose a method called local dimensionality regularization (LDReg). Our formulation is based on the derivation of the Fisher-Rao metric to compare and optimize local distance distributions at an asymptotically small radius for each data point. By increasing the local intrinsic dimensionality, we demonstrate through a range of experiments that LDReg improves the representation quality of SSL. The results also show that LDReg can regularize dimensionality at both local and global levels.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2401.10474")

Code

Syntology Ran 20 of 36 code samples harvested from 2 repositories linked to this paper; 16 have no recorded run. Of those that ran: 4 ran · honoured contract; 1 ran · violated contract; 2 ran · our draft was wrong; 6 ran · fixture could not drive it; 7 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 5 ran; community (archive-listed): 30 samples from 1 repository, 15 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

HanxunH/LDReg officialmentioned in papermentioned on GitHubpytorch report
JoJoNing25/DDAug mentioned on GitHubpytorch 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

36 samples harvested; 20 ran; 4 honoured the contract we drafted; 16 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
6ran · fixture could not drive it
7ran
16unverified

Licence: 0 of the 36 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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

NTXentBase HanxunH/LDReg/losses/ntxent_lid_reg.py official repository ran MIT (permissive) · f3d6a6be48cdb9e9 · report
accuracy HanxunH/LDReg/losses/ntxent_lid_reg.py official repository ran · fixture could not drive it MIT (permissive) · e8d9c82a15ba2a57 · report
gather HanxunH/LDReg/losses/ntxent_lid_reg.py official repository ran · our draft was wrong MIT (permissive) · cf0782bfe6eddbac · report
lid_mle HanxunH/LDReg/losses/ntxent_lid_reg.py official repository ran · fixture could not drive it MIT (permissive) · 9d8f2e35d4702814 · report
lid_mom_est HanxunH/LDReg/losses/ntxent_lid_reg.py official repository ran · fixture could not drive it MIT (permissive) · 918cecffdec2a619 · report
NTXentLIDReg HanxunH/LDReg/losses/ntxent_lid_reg.py official repository unverified MIT (permissive) · 0cfb402f67dc5765 · report
FullGatherLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran MIT (permissive) · efbec016cf3c4e21 · report
GrayLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · d03096e93a9cffcc · report
IdentityLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · dcb240bf1416737e · report
_STE JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran MIT (permissive) · 0948c0465513c79d · report
_blend_image JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 3bccd0b613b2ec94 · report
_blur JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 00b297b23155ccd0 · report
_gray JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 14a3e0d0584f4f1f · report
activation JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · cd6af889cd96c427 · report
eye_rank JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · 4593546c432138ea · report
get_sharpness_kernel JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · honoured contract MIT (permissive) · a77358b38f7eb68c · report
lid_mle JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 397aafa38e8e9bfa · report
rank JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · metamorphic tier: well formed MIT (permissive) · a38b33a0219b2651 · report
ste JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · f8ccb18e75fab7db · report
tensor_function JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 229e3f0e1a7ceb04 · report
world_size JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) ran · metamorphic tier: well formed MIT (permissive) · a1d11ea20c97a5b5 · report
AugLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 8758e55ff0b748ef · report
AugPolicy JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 99feec893219b44d · report
BrightnessLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 5872bbeca7913d9c · report
ContrastLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · c566f6618abd39ed · report
GaussianBlurLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 83b86abab1e05654 · report
HueLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 057cf4bcc8260a07 · report
NTXentLossLIDAug JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 5887614dd9999cbd · report
PosterizeLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 712473be9274437d · report
SaturationLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · c2f2a5f8fcf3adac · report
SharpnessLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 7b025f0f036c7b4c · report
SolarizeLayer JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · ef94ac6f4485c581 · report
full_gather JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 18ac34711a665335 · report
posterize JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 01c6078e675ae833 · report
sharpness JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 959973c5950dd3fb · report
solarize JoJoNing25/DDAug/losses/ntxent_lidaug.py community (archive-listed) unverified MIT (permissive) · 8000f04f9e183df4 · report

Tasks

Self-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