{"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/la-maml-look-ahead-meta-learning-for","title":"La-MAML: Look-ahead Meta Learning for Continual Learning","arxiv_id":"2007.13904","date":"2020-07-27","proceeding":"ICML Workshop LifelongML 2020 7","authors":["Gunshi Gupta","Karmesh Yadav","Liam Paull"],"abstract":"The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks. While meta-learning shows great potential for reducing interference between old and new tasks, the current training procedures tend to be either slow or offline, and sensitive to many hyper-parameters. In this work, we propose Look-ahead MAML (La-MAML), a fast optimisation-based meta-learning algorithm for online-continual learning, aided by a small episodic memory. Our proposed modulation of per-parameter learning rates in our meta-learning update allows us to draw connections to prior work on hypergradients and meta-descent. This provides a more flexible and efficient way to mitigate catastrophic forgetting compared to conventional prior-based methods. La-MAML achieves performance superior to other replay-based, prior-based and meta-learning based approaches for continual learning on real-world visual classification benchmarks. Source code can be found here: https://github.com/montrealrobotics/La-MAML","url_abs":"https://arxiv.org/abs/2007.13904v2","url_pdf":"https://arxiv.org/pdf/2007.13904v2.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":"la-maml-look-ahead-meta-learning-for","repo_url":"https://github.com/montrealrobotics/La-MAML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"la-maml-look-ahead-meta-learning-for","repo_url":"https://github.com/joeljosephjin/La-MAML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"la-maml-look-ahead-meta-learning-for","repo_url":"https://github.com/ContinualAI/avalanche","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"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=2007.13904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.13904"}},"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/joeljosephjin/La-MAML","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ContinualAI/avalanche","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/montrealrobotics/La-MAML","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"ran_honours":1,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":1,"repositories":1},"listed":{"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":"962ddb6734b77774","entry":"AMLCriterion","repo":"ContinualAI/avalanche","repo_kind":"listed","path":"avalanche/training/regularization.py","file_url":"https://github.com/ContinualAI/avalanche/blob/HEAD/avalanche/training/regularization.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"962ddb6734b77774"}},{"code_sha256_prefix":"8e0b727c87e1e311","entry":"compute_offsets","repo":"montrealrobotics/La-MAML","repo_kind":"official","path":"model/agem.py","file_url":"https://github.com/montrealrobotics/La-MAML/blob/HEAD/model/agem.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8e0b727c87e1e311"}},{"code_sha256_prefix":"c786263dfd96b80c","entry":"deprecated","repo":"ContinualAI/avalanche","repo_kind":"listed","path":"avalanche/training/regularization.py","file_url":"https://github.com/ContinualAI/avalanche/blob/HEAD/avalanche/training/regularization.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c786263dfd96b80c"}},{"code_sha256_prefix":"5046ac899e4b1bd1","entry":"RegularizationMethod","repo":"ContinualAI/avalanche","repo_kind":"listed","path":"avalanche/training/regularization.py","file_url":"https://github.com/ContinualAI/avalanche/blob/HEAD/avalanche/training/regularization.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5046ac899e4b1bd1"}},{"code_sha256_prefix":"a22bdeae0fe7a0e0","entry":"eval_iid_tasks","repo":"montrealrobotics/La-MAML","repo_kind":"official","path":"main_multi_task.py","file_url":"https://github.com/montrealrobotics/La-MAML/blob/HEAD/main_multi_task.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":"a22bdeae0fe7a0e0"}},{"code_sha256_prefix":"4d111c06e63ce0ba","entry":"life_experience_iid","repo":"montrealrobotics/La-MAML","repo_kind":"official","path":"main_multi_task.py","file_url":"https://github.com/montrealrobotics/La-MAML/blob/HEAD/main_multi_task.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":"4d111c06e63ce0ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}