{"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/learning-with-recoverable-forgetting","title":"Learning with Recoverable Forgetting","arxiv_id":"2207.08224","date":"2022-07-17","proceeding":null,"authors":["Jingwen Ye","Yifang Fu","Jie Song","Xingyi Yang","Songhua Liu","Xin Jin","Mingli Song","Xinchao Wang"],"abstract":"Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge. However, the involved training data may not be life-long legitimate due to privacy or copyright reasons. In practical scenarios, for instance, the model owner may wish to enable or disable the knowledge of specific tasks or specific samples from time to time. Such flexible control over knowledge transfer, unfortunately, has been largely overlooked in previous incremental or decremental learning methods, even at a problem-setup level. In this paper, we explore a novel learning scheme, termed as Learning wIth Recoverable Forgetting (LIRF), that explicitly handles the task- or sample-specific knowledge removal and recovery. Specifically, LIRF brings in two innovative schemes, namely knowledge deposit and withdrawal, which allow for isolating user-designated knowledge from a pre-trained network and injecting it back when necessary. During the knowledge deposit process, the specified knowledge is extracted from the target network and stored in a deposit module, while the insensitive or general knowledge of the target network is preserved and further augmented. During knowledge withdrawal, the taken-off knowledge is added back to the target network. The deposit and withdraw processes only demand for a few epochs of finetuning on the removal data, ensuring both data and time efficiency. We conduct experiments on several datasets, and demonstrate that the proposed LIRF strategy yields encouraging results with gratifying generalization capability.","url_abs":"https://arxiv.org/abs/2207.08224v1","url_pdf":"https://arxiv.org/pdf/2207.08224v1.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":"learning-with-recoverable-forgetting","repo_url":"https://github.com/JngwenYe/LIRF","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"general-knowledge","task_name":"General Knowledge"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.08224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.08224"}},"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/JngwenYe/LIRF","reach":null}],"summary":{"ran":2,"unverified":2},"by_repo_kind":{"listed":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"3cff5e2594924336","entry":"AT","repo":"JngwenYe/LIRF","repo_kind":"listed","path":"train_deposit.py","file_url":"https://github.com/JngwenYe/LIRF/blob/HEAD/train_deposit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3cff5e2594924336"}},{"code_sha256_prefix":"eaf2458f9d97ad61","entry":"RunningAverage","repo":"JngwenYe/LIRF","repo_kind":"listed","path":"train_deposit.py","file_url":"https://github.com/JngwenYe/LIRF/blob/HEAD/train_deposit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eaf2458f9d97ad61"}},{"code_sha256_prefix":"497a170899674f77","entry":"loss_fn_kd","repo":"JngwenYe/LIRF","repo_kind":"listed","path":"train_deposit.py","file_url":"https://github.com/JngwenYe/LIRF/blob/HEAD/train_deposit.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":"497a170899674f77"}},{"code_sha256_prefix":"c4cc6b3852caf181","entry":"train_epoch_kd","repo":"JngwenYe/LIRF","repo_kind":"listed","path":"train_deposit.py","file_url":"https://github.com/JngwenYe/LIRF/blob/HEAD/train_deposit.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":"c4cc6b3852caf181"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}