{"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/three-scenarios-for-continual-learning","title":"Three scenarios for continual learning","arxiv_id":"1904.07734","date":"2019-04-15","proceeding":null,"authors":["Gido M. van de Ven","Andreas S. Tolias"],"abstract":"Standard artificial neural networks suffer from the well-known issue of\ncatastrophic forgetting, making continual or lifelong learning difficult for\nmachine learning. In recent years, numerous methods have been proposed for\ncontinual learning, but due to differences in evaluation protocols it is\ndifficult to directly compare their performance. To enable more structured\ncomparisons, we describe three continual learning scenarios based on whether at\ntest time task identity is provided and--in case it is not--whether it must be\ninferred. Any sequence of well-defined tasks can be performed according to each\nscenario. Using the split and permuted MNIST task protocols, for each scenario\nwe carry out an extensive comparison of recently proposed continual learning\nmethods. We demonstrate substantial differences between the three scenarios in\nterms of difficulty and in terms of how efficient different methods are. In\nparticular, when task identity must be inferred (i.e., class incremental\nlearning), we find that regularization-based approaches (e.g., elastic weight\nconsolidation) fail and that replaying representations of previous experiences\nseems required for solving this scenario.","url_abs":"http://arxiv.org/abs/1904.07734v1","url_pdf":"http://arxiv.org/pdf/1904.07734v1.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":"three-scenarios-for-continual-learning","repo_url":"https://github.com/GMvandeVen/continual-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"three-scenarios-for-continual-learning","repo_url":"https://github.com/GMvandeVen/complex-synapses","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"three-scenarios-for-continual-learning","repo_url":"https://github.com/WangTianduo/lifelong-learning-3-cases","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"three-scenarios-for-continual-learning","repo_url":"https://github.com/XSMUBC/DNC-lifelong-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"three-scenarios-for-continual-learning","repo_url":"https://github.com/XSMUBC/Lifelong-learning_xsm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"three-scenarios-for-continual-learning","repo_url":"https://github.com/gahaalt/continual-learning-overview","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"three-scenarios-for-continual-learning","repo_url":"https://github.com/gahaalt/continual-learning-with-hypernets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"three-scenarios-for-continual-learning","repo_url":"https://github.com/llzlcl/Continual-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"lifelong-learning","task_name":"Lifelong learning"},{"task_slug":null,"task_name":"Permuted-MNIST"},{"task_slug":"class-incremental-learning-1","task_name":"class-incremental learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.07734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.07734"}},"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/GMvandeVen/continual-learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gahaalt/continual-learning-overview","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/WangTianduo/lifelong-learning-3-cases","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gahaalt/continual-learning-with-hypernets","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XSMUBC/DNC-lifelong-learning","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/llzlcl/Continual-Learning","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/XSMUBC/Lifelong-learning_xsm","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/GMvandeVen/complex-synapses","reach":{"status":"ok"}}],"summary":{"unverified":2},"by_repo_kind":{"listed":{"samples":2,"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":"a5d42513905f6442","entry":"get_dataset","repo":"WangTianduo/lifelong-learning-3-cases","repo_kind":"listed","path":"data.py","file_url":"https://github.com/WangTianduo/lifelong-learning-3-cases/blob/HEAD/data.py","link_basis":"harvester_set","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":"a5d42513905f6442"}},{"code_sha256_prefix":"a99bc1039b57a869","entry":"linearExcitability","repo":"WangTianduo/lifelong-learning-3-cases","repo_kind":"listed","path":"excitability_modules.py","file_url":"https://github.com/WangTianduo/lifelong-learning-3-cases/blob/HEAD/excitability_modules.py","link_basis":"harvester_set","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":"a99bc1039b57a869"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}