{"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/how-to-train-your-maml","title":"How to train your MAML","arxiv_id":"1810.09502","date":"2018-10-22","proceeding":"ICLR 2019 5","authors":["Antreas Antoniou","Harrison Edwards","Amos Storkey"],"abstract":"The field of few-shot learning has recently seen substantial advancements.\nMost of these advancements came from casting few-shot learning as a\nmeta-learning problem. Model Agnostic Meta Learning or MAML is currently one of\nthe best approaches for few-shot learning via meta-learning. MAML is simple,\nelegant and very powerful, however, it has a variety of issues, such as being\nvery sensitive to neural network architectures, often leading to instability\nduring training, requiring arduous hyperparameter searches to stabilize\ntraining and achieve high generalization and being very computationally\nexpensive at both training and inference times. In this paper, we propose\nvarious modifications to MAML that not only stabilize the system, but also\nsubstantially improve the generalization performance, convergence speed and\ncomputational overhead of MAML, which we call MAML++.","url_abs":"http://arxiv.org/abs/1810.09502v3","url_pdf":"http://arxiv.org/pdf/1810.09502v3.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":"how-to-train-your-maml","repo_url":"https://github.com/AntreasAntoniou/HowToTrainYourMAMLPytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"how-to-train-your-maml","repo_url":"https://github.com/JWSoh/MZSR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"how-to-train-your-maml","repo_url":"https://github.com/Tikquuss/meta_XLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"how-to-train-your-maml","repo_url":"https://github.com/dkalpakchi/ReproducingSCAPytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"how-to-train-your-maml","repo_url":"https://github.com/gebob19/REPTILE-Metalearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"how-to-train-your-maml","repo_url":"https://github.com/gebob19/cscd94-metalearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"how-to-train-your-maml","repo_url":"https://github.com/gebob19/cscd94_metalearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"how-to-train-your-maml","repo_url":"https://github.com/hfahrudin/reptile_implement_tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"how-to-train-your-maml","repo_url":"https://github.com/hoyeoplee/pytorch-maml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"how-to-train-your-maml","repo_url":"https://github.com/lgcollins/tr-maml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-image-classification","task_name":"Few-Shot Image Classification"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"maml","method_name":"MAML"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-image-classification-on-mini-2","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (1-shot)","model":"MAML++","rank_in_archive_order":91,"of":105,"metrics":{"Accuracy":"52.40"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-mini-3","task":"Few-Shot Image Classification","dataset":"Mini-Imagenet 5-way (5-shot)","model":"MAML++","rank_in_archive_order":88,"of":95,"metrics":{"Accuracy":"67.15"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-1-1","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 1-Shot, 20-way","model":"MAML++","rank_in_archive_order":6,"of":20,"metrics":{"Accuracy":"97.65"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-1-2","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 1-Shot, 5-way","model":"MAML++","rank_in_archive_order":7,"of":17,"metrics":{"Accuracy":"99.47"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-5-1","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 5-Shot, 20-way","model":"MAML++","rank_in_archive_order":5,"of":19,"metrics":{"Accuracy":"99.33%"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-image-classification-on-omniglot-5-2","task":"Few-Shot Image Classification","dataset":"OMNIGLOT - 5-Shot, 5-way","model":"MAML++","rank_in_archive_order":6,"of":16,"metrics":{"Accuracy":"99.85%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.09502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.09502"}},"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/gebob19/REPTILE-Metalearning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AntreasAntoniou/HowToTrainYourMAMLPytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Tikquuss/meta_XLM","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lgcollins/tr-maml","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hoyeoplee/pytorch-maml","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JWSoh/MZSR","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gebob19/cscd94_metalearning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hfahrudin/reptile_implement_tf2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dkalpakchi/ReproducingSCAPytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gebob19/cscd94-metalearning","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{},"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":1,"samples":[{"code_sha256_prefix":"5c44538154dad8a7","entry":"set_torch_seed","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"5c44538154dad8a7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}