Papers › Max-Margin Contrastive Learning

Max-Margin Contrastive Learning

21 Dec 2021arXiv:2112.11450archive 2025-07-28

Anshul Shah, Suvrit Sra, Rama Chellappa, Anoop Cherian

Standard contrastive learning approaches usually require a large number of negatives for effective unsupervised learning and often exhibit slow convergence. We suspect this behavior is due to the suboptimal selection of negatives used for offering contrast to the positives. We counter this difficulty by taking inspiration from support vector machines (SVMs) to present max-margin contrastive learning (MMCL). Our approach selects negatives as the sparse support vectors obtained via a quadratic optimization problem, and contrastiveness is enforced by maximizing the decision margin. As SVM optimization can be computationally demanding, especially in an end-to-end setting, we present simplifications that alleviate the computational burden. We validate our approach on standard vision benchmark datasets, demonstrating better performance in unsupervised representation learning over state-of-the-art, while having better empirical convergence properties.

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="2112.11450")

Code

Syntology Ran 2 of 12 code samples harvested from 1 repository linked to this paper; 10 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

anshulbshah/MMCL officialmentioned 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

12 samples harvested; 2 ran; 1 honoured the contract we drafted; 10 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 · honoured contract
1ran
10unverified

Licence: 0 of the 12 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 anshulbshah/MMCL. “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 anshulbshah/MMCL/models/losses.py official repository ran MIT (permissive) · 11bc56dd2ecb7644 · report
get_lr anshulbshah/MMCL/CIFAR100/linear.py official repository ran · honoured contract MIT (permissive) · 7337f1f5ff01dcd0 · report
compute_kernel anshulbshah/MMCL/models/losses.py official repository unverified MIT (permissive) · 9498c0875cc30496 · report
compute_kernel_new anshulbshah/MMCL/CIFAR100/svm_losses.py official repository unverified MIT (permissive) · 5fa7bb56e6e22a54 · report
get_args anshulbshah/MMCL/myexman/index.py official repository unverified MIT (permissive) · 5bd550cf0a598b22 · report
get_dataset anshulbshah/MMCL/CIFAR100/utils.py official repository unverified MIT (permissive) · 0b30248ddcadc9b7 · report
none2none anshulbshah/MMCL/myexman/index.py official repository unverified MIT (permissive) · 459939c749c8fd3f · report
only_value_error anshulbshah/MMCL/myexman/index.py official repository unverified MIT (permissive) · c404ad6b3c3cae86 · report
pgd_simple_short anshulbshah/MMCL/models/solvers.py official repository unverified MIT (permissive) · 54bdbe97f492c455 · report
pgd_with_nesterov anshulbshah/MMCL/models/solvers.py official repository unverified MIT (permissive) · 5a39dd9aa51e8d32 · report
pgd_with_nesterov anshulbshah/MMCL/CIFAR100/solvers.py official repository unverified MIT (permissive) · 91f52fbcbca3f103 · report
train_val anshulbshah/MMCL/CIFAR100/linear.py official repository unverified MIT (permissive) · 8f49bc51cbbd9f64 · report

Tasks

Contrastive LearningRepresentation LearningSelf-Supervised Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Image Classification ImageNet MMCL (100 epoch, 256 batch size) Top 1 Accuracy 63.8% #116 of 144 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Contrastive LearningSVM

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