{"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/online-fast-adaptation-and-knowledge","title":"Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning","arxiv_id":"2003.05856","date":"2020-03-12","proceeding":"NeurIPS 2020 12","authors":["Massimo Caccia","Pau Rodriguez","Oleksiy Ostapenko","Fabrice Normandin","Min Lin","Lucas Caccia","Issam Laradji","Irina Rish","Alexandre Lacoste","David Vazquez","Laurent Charlin"],"abstract":"Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened new avenues of research. In meta-continual learning, the model is pre-trained to minimize catastrophic forgetting of previous tasks. In continual-meta learning, the aim is to train agents for faster remembering of previous tasks through adaptation. In their original formulations, both methods have limitations. We stand on their shoulders to propose a more general scenario, OSAKA, where an agent must quickly solve new (out-of-distribution) tasks, while also requiring fast remembering. We show that current continual learning, meta-learning, meta-continual learning, and continual-meta learning techniques fail in this new scenario. We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario. We empirically show that Continual-MAML is better suited to the new scenario than the aforementioned methodologies, as well as standard continual learning and meta-learning approaches.","url_abs":"https://arxiv.org/abs/2003.05856v3","url_pdf":"https://arxiv.org/pdf/2003.05856v3.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":"online-fast-adaptation-and-knowledge","repo_url":"https://github.com/ElementAI/osaka","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"maml","method_name":"MAML"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.05856","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05856"}},"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/ElementAI/osaka","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"f6e56b6b372b808c","entry":"bgd","repo":"ElementAI/osaka","repo_kind":"official","path":"Utils/bgd_lib/optimizers_lib.py","file_url":"https://github.com/ElementAI/osaka/blob/HEAD/Utils/bgd_lib/optimizers_lib.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":"f6e56b6b372b808c"}},{"code_sha256_prefix":"58242025465b988c","entry":"compute_accuracy","repo":"ElementAI/osaka","repo_kind":"official","path":"MAML/utils.py","file_url":"https://github.com/ElementAI/osaka/blob/HEAD/MAML/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":"58242025465b988c"}},{"code_sha256_prefix":"ae24f4a845993694","entry":"init_dataloaders","repo":"ElementAI/osaka","repo_kind":"official","path":"dataloaders.py","file_url":"https://github.com/ElementAI/osaka/blob/HEAD/dataloaders.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":"ae24f4a845993694"}},{"code_sha256_prefix":"347d435fde28d569","entry":"order_and_split","repo":"ElementAI/osaka","repo_kind":"official","path":"dataloaders.py","file_url":"https://github.com/ElementAI/osaka/blob/HEAD/dataloaders.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":"347d435fde28d569"}},{"code_sha256_prefix":"a63a949e02651b46","entry":"select_from_tensor","repo":"ElementAI/osaka","repo_kind":"official","path":"dataloaders.py","file_url":"https://github.com/ElementAI/osaka/blob/HEAD/dataloaders.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":"a63a949e02651b46"}},{"code_sha256_prefix":"c0ddd2704ec5ba06","entry":"str2bool","repo":"ElementAI/osaka","repo_kind":"official","path":"args.py","file_url":"https://github.com/ElementAI/osaka/blob/HEAD/args.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":"c0ddd2704ec5ba06"}},{"code_sha256_prefix":"e78673d4bdd6ad3c","entry":"tensors_to_device","repo":"ElementAI/osaka","repo_kind":"official","path":"MAML/utils.py","file_url":"https://github.com/ElementAI/osaka/blob/HEAD/MAML/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":"e78673d4bdd6ad3c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}