Papers › Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning

Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning

24 Jun 2023arXiv:2306.13924archive 2025-07-28

Sharut Gupta, Joshua Robinson, Derek Lim, Soledad Villar, Stefanie Jegelka

Self-supervised learning converts raw perceptual data such as images to a compact space where simple Euclidean distances measure meaningful variations in data. In this paper, we extend this formulation by adding additional geometric structure to the embedding space by enforcing transformations of input space to correspond to simple (i.e., linear) transformations of embedding space. Specifically, in the contrastive learning setting, we introduce an equivariance objective and theoretically prove that its minima forces augmentations on input space to correspond to rotations on the spherical embedding space. We show that merely combining our equivariant loss with a non-collapse term results in non-trivial representations, without requiring invariance to data augmentations. Optimal performance is achieved by also encouraging approximate invariance, where input augmentations correspond to small rotations. Our method, CARE: Contrastive Augmentation-induced Rotational Equivariance, leads to improved performance on downstream tasks, and ensures sensitivity in embedding space to important variations in data (e.g., color) that standard contrastive methods do not achieve. Code is available at https://github.com/Sharut/CARE.

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="2306.13924")

Code

Syntology Ran 1 of 15 code samples harvested from 1 repository linked to this paper; 14 have no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: official repository: 15 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sharut/care officialmentioned in papermentioned on GitHubpytorchMIT 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; 1 ran; 0 honoured the contract we drafted; 14 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.

1ran · fixture could not drive it
14unverified

Licence: 0 of the 15 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 sharut/care. “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.

accuracy sharut/care/imagenet100/main_lincls.py official repository ran · fixture could not drive it MIT (permissive) · 131a82fd65128218 · report
TorchGaussianBlur sharut/care/cifar10_cifar100_stl10/dataset.py official repository unverified MIT (permissive) · f085c9c27837dc79 · report
compute_similarities sharut/care/imagenet100/log.py official repository unverified MIT (permissive) · 01a8b7a49a68c9c9 · report
compute_similarities sharut/care/cifar10_cifar100_stl10/log.py official repository unverified MIT (permissive) · 9c7e58c47f3d6658 · report
concat_all_gather sharut/care/imagenet100/model/builder.py official repository unverified MIT (permissive) · 73cecca9f3575f09 · report
extract_lr sharut/care/imagenet100/log.py official repository unverified MIT (permissive) · bde665611cfb0d27 · report
get_dataset sharut/care/cifar10_cifar100_stl10/dataset.py official repository unverified MIT (permissive) · 6d94ccf3eb7d9607 · report
get_info sharut/care/imagenet100/model/loss.py official repository unverified MIT (permissive) · ec0e9d4fc69533ae · report
get_negative_mask sharut/care/cifar10_cifar100_stl10/utils.py official repository unverified MIT (permissive) · b09a2cc2e21f2012 · report
get_optimizer sharut/care/cifar10_cifar100_stl10/utils.py official repository unverified MIT (permissive) · 825885e5fbd21be1 · report
get_transforms sharut/care/cifar10_cifar100_stl10/dataset.py official repository unverified MIT (permissive) · 42041b30a3a877a3 · report
knn sharut/care/imagenet100/log.py official repository unverified MIT (permissive) · 0f2efd3cafe29242 · report
loss sharut/care/imagenet100/model/loss.py official repository unverified MIT (permissive) · 1e8ed9ddd670ec26 · report
train_val sharut/care/cifar10_cifar100_stl10/linear.py official repository unverified MIT (permissive) · 55b8283c8e8503b3 · report
validate sharut/care/imagenet100/main_lincls.py official repository unverified MIT (permissive) · 6a1484b1e8271a28 · report

Tasks

Contrastive LearningSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive Learning

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