{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/comatch-semi-supervised-learning-with","title":"CoMatch: Semi-supervised Learning with Contrastive Graph Regularization","arxiv_id":"2011.11183","date":"2020-11-23","proceeding":"ICCV 2021 10","authors":["Junnan Li","Caiming Xiong","Steven Hoi"],"abstract":"Semi-supervised learning has been an effective paradigm for leveraging unlabeled data to reduce the reliance on labeled data. We propose CoMatch, a new semi-supervised learning method that unifies dominant approaches and addresses their limitations. CoMatch jointly learns two representations of the training data, their class probabilities and low-dimensional embeddings. The two representations interact with each other to jointly evolve. The embeddings impose a smoothness constraint on the class probabilities to improve the pseudo-labels, whereas the pseudo-labels regularize the structure of the embeddings through graph-based contrastive learning. CoMatch achieves state-of-the-art performance on multiple datasets. It achieves substantial accuracy improvements on the label-scarce CIFAR-10 and STL-10. On ImageNet with 1% labels, CoMatch achieves a top-1 accuracy of 66.0%, outperforming FixMatch by 12.6%. Furthermore, CoMatch achieves better representation learning performance on downstream tasks, outperforming both supervised learning and self-supervised learning. Code and pre-trained models are available at https://github.com/salesforce/CoMatch.","url_abs":"https://arxiv.org/abs/2011.11183v2","url_pdf":"https://arxiv.org/pdf/2011.11183v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"comatch-semi-supervised-learning-with","repo_url":"https://github.com/salesforce/CoMatch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"comatch-semi-supervised-learning-with","repo_url":"https://github.com/LKLQQ/ssc_resnet50","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"unanswered"}},{"paper_slug":"comatch-semi-supervised-learning-with","repo_url":"https://github.com/ptrckhmmr/learning-to-defer-with-limited-expert-predictions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"semi-supervised-image-classification","task_name":"Semi-Supervised Image Classification"}],"methods":[{"method_slug":"fixmatch","method_name":"FixMatch"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-15","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 20 Labels","model":"CoMatch (SimCLR)","rank_in_archive_order":2,"of":3,"metrics":{"Percentage error":"12.33±8.47"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-7","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 40 Labels","model":"CoMatch (w. SimCLR)","rank_in_archive_order":15,"of":21,"metrics":{"Percentage error":"6.91±1.39"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-cifar-16","task":"Semi-Supervised Image Classification","dataset":"CIFAR-10, 80 Labels","model":"SimCLR (CoMatch)","rank_in_archive_order":2,"of":2,"metrics":{"Percentage error":"5.98"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-1","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 1% labeled data","model":"CoMatch (w. MoCo v2)","rank_in_archive_order":28,"of":65,"metrics":{"Top 1 Accuracy":"67.1%","Top 5 Accuracy":"87.1%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-2","task":"Semi-Supervised Image Classification","dataset":"ImageNet - 10% labeled data","model":"CoMatch (w. MoCo v2)","rank_in_archive_order":35,"of":75,"metrics":{"Top 1 Accuracy":"73.7%","Top 5 Accuracy":"91.4%"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-image-classification-on-stl-1","task":"Semi-Supervised Image Classification","dataset":"STL-10, 1000 Labels","model":"SimCLR (CoMatch)","rank_in_archive_order":12,"of":13,"metrics":{"Accuracy":"77.46"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.11183","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.11183"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ptrckhmmr/learning-to-defer-with-limited-expert-predictions","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LKLQQ/ssc_resnet50","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/salesforce/CoMatch","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"138a74a987d42767","entry":"setup_default_logging","repo":"salesforce/CoMatch","repo_kind":"official","path":"imagenet/Train_CoMatch.py","file_url":"https://github.com/salesforce/CoMatch/blob/HEAD/imagenet/Train_CoMatch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"138a74a987d42767"}},{"code_sha256_prefix":"8407a16806957372","entry":"time_str","repo":"salesforce/CoMatch","repo_kind":"official","path":"imagenet/Train_CoMatch.py","file_url":"https://github.com/salesforce/CoMatch/blob/HEAD/imagenet/Train_CoMatch.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"8407a16806957372"}},{"code_sha256_prefix":"9cffb9ca3a85eea4","entry":"validate","repo":"salesforce/CoMatch","repo_kind":"official","path":"imagenet/Train_CoMatch.py","file_url":"https://github.com/salesforce/CoMatch/blob/HEAD/imagenet/Train_CoMatch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"9cffb9ca3a85eea4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}