{"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/platinum-semi-supervised-model-agnostic-meta","title":"PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information","arxiv_id":"2201.12928","date":"2022-01-30","proceeding":null,"authors":["Changbin Li","Suraj Kothawade","Feng Chen","Rishabh Iyer"],"abstract":"Few-shot classification (FSC) requires training models using a few (typically one to five) data points per class. Meta learning has proven to be able to learn a parametrized model for FSC by training on various other classification tasks. In this work, we propose PLATINUM (semi-suPervised modeL Agnostic meTa-learnIng usiNg sUbmodular Mutual information), a novel semi-supervised model agnostic meta-learning framework that uses the submodular mutual information (SMI) functions to boost the performance of FSC. PLATINUM leverages unlabeled data in the inner and outer loop using SMI functions during meta-training and obtains richer meta-learned parameterizations for meta-test. We study the performance of PLATINUM in two scenarios - 1) where the unlabeled data points belong to the same set of classes as the labeled set of a certain episode, and 2) where there exist out-of-distribution classes that do not belong to the labeled set. We evaluate our method on various settings on the miniImageNet, tieredImageNet and Fewshot-CIFAR100 datasets. Our experiments show that PLATINUM outperforms MAML and semi-supervised approaches like pseduo-labeling for semi-supervised FSC, especially for small ratio of labeled examples per class.","url_abs":"https://arxiv.org/abs/2201.12928v2","url_pdf":"https://arxiv.org/pdf/2201.12928v2.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":"platinum-semi-supervised-model-agnostic-meta","repo_url":"https://github.com/hugo101/platinum","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"maml","method_name":"MAML"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2201.12928","atlas_url":"https://app.syntology.ai/?focus=2201.12928","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.12928"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/Hugo101/PLATINUM","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hugo101/platinum","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"9fd162f52ef249fd","entry":"append_data","repo":"hugo101/platinum","repo_kind":"official","path":"maml_ssl_main.py","file_url":"https://github.com/hugo101/platinum/blob/HEAD/maml_ssl_main.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fd162f52ef249fd"}},{"code_sha256_prefix":"0c1b3df9d1259f0e","entry":"cat_data","repo":"hugo101/platinum","repo_kind":"official","path":"maml_ssl_main.py","file_url":"https://github.com/hugo101/platinum/blob/HEAD/maml_ssl_main.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c1b3df9d1259f0e"}},{"code_sha256_prefix":"74343f0c3133e4e2","entry":"remove_overlap","repo":"hugo101/platinum","repo_kind":"official","path":"lib_SSL/algs/smi_function_vanilla.py","file_url":"https://github.com/hugo101/platinum/blob/HEAD/lib_SSL/algs/smi_function_vanilla.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"74343f0c3133e4e2"}},{"code_sha256_prefix":"d30990713e0730be","entry":"smi_pl_loss","repo":"hugo101/platinum","repo_kind":"official","path":"lib_SSL/algs/smi_function_vanilla.py","file_url":"https://github.com/hugo101/platinum/blob/HEAD/lib_SSL/algs/smi_function_vanilla.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d30990713e0730be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}