{"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/combining-mixmatch-and-active-learning-for-1","title":"Combining MixMatch and Active Learning for Better Accuracy with Fewer Labels","arxiv_id":"1912.00594","date":"2019-12-02","proceeding":null,"authors":["Shuang Song","David Berthelot","Afshin Rostamizadeh"],"abstract":"We propose using active learning based techniques to further improve the state-of-the-art semi-supervised learning MixMatch algorithm. We provide a thorough empirical evaluation of several active-learning and baseline methods, which successfully demonstrate a significant improvement on the benchmark CIFAR-10, CIFAR-100, and SVHN datasets (as much as 1.5% in absolute accuracy). We also provide an empirical analysis of the cost trade-off between incrementally gathering more labeled versus unlabeled data. This analysis can be used to measure the relative value of labeled/unlabeled data at different points of the learning curve, where we find that although the incremental value of labeled data can be as much as 20x that of unlabeled, it quickly diminishes to less than 3x once more than 2,000 labeled example are observed. Code can be found at https://github.com/google-research/mma.","url_abs":"https://arxiv.org/abs/1912.00594v2","url_pdf":"https://arxiv.org/pdf/1912.00594v2.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":"combining-mixmatch-and-active-learning-for-1","repo_url":"https://github.com/google-research/mma","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1912.00594","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.00594"}},"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/google-research/mma","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"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":"1b71a50832a4d7c7","entry":"entropy_from_logits","repo":"google-research/mma","repo_kind":"official","path":"libml/layers.py","file_url":"https://github.com/google-research/mma/blob/HEAD/libml/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1b71a50832a4d7c7"}},{"code_sha256_prefix":"8eaf2dd04cef57b0","entry":"entropy_penalty","repo":"google-research/mma","repo_kind":"official","path":"libml/layers.py","file_url":"https://github.com/google-research/mma/blob/HEAD/libml/layers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8eaf2dd04cef57b0"}},{"code_sha256_prefix":"f2880ff3aa20a21d","entry":"find_latest_checkpoint","repo":"google-research/mma","repo_kind":"official","path":"libml/utils.py","file_url":"https://github.com/google-research/mma/blob/HEAD/libml/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f2880ff3aa20a21d"}},{"code_sha256_prefix":"6f13728738e30339","entry":"ilog2","repo":"google-research/mma","repo_kind":"official","path":"libml/utils.py","file_url":"https://github.com/google-research/mma/blob/HEAD/libml/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6f13728738e30339"}},{"code_sha256_prefix":"aff7665c93b61326","entry":"record_parse","repo":"google-research/mma","repo_kind":"official","path":"libml/data.py","file_url":"https://github.com/google-research/mma/blob/HEAD/libml/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"aff7665c93b61326"}},{"code_sha256_prefix":"2d71b7b23ae3fb60","entry":"record_parse_mnist","repo":"google-research/mma","repo_kind":"official","path":"libml/data.py","file_url":"https://github.com/google-research/mma/blob/HEAD/libml/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d71b7b23ae3fb60"}},{"code_sha256_prefix":"5d6c5e891d55bfa2","entry":"record_parse_orig","repo":"google-research/mma","repo_kind":"official","path":"libml/data.py","file_url":"https://github.com/google-research/mma/blob/HEAD/libml/data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d6c5e891d55bfa2"}},{"code_sha256_prefix":"5d8684fa279a5f80","entry":"smart_shape","repo":"google-research/mma","repo_kind":"official","path":"libml/layers.py","file_url":"https://github.com/google-research/mma/blob/HEAD/libml/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5d8684fa279a5f80"}},{"code_sha256_prefix":"9fff382323a34e5a","entry":"smart_shape","repo":"google-research/mma","repo_kind":"official","path":"libml/utils.py","file_url":"https://github.com/google-research/mma/blob/HEAD/libml/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9fff382323a34e5a"}},{"code_sha256_prefix":"91ff834ad095a129","entry":"stack_augment","repo":"google-research/mma","repo_kind":"official","path":"libml/data_pair.py","file_url":"https://github.com/google-research/mma/blob/HEAD/libml/data_pair.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"91ff834ad095a129"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}