{"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/fortuitous-forgetting-in-connectionist-1","title":"Fortuitous Forgetting in Connectionist Networks","arxiv_id":"2202.00155","date":"2022-02-01","proceeding":"ICLR 2022 4","authors":["Hattie Zhou","Ankit Vani","Hugo Larochelle","Aaron Courville"],"abstract":"Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact be favorable to learning. We introduce \"forget-and-relearn\" as a powerful paradigm for shaping the learning trajectories of artificial neural networks. In this process, the forgetting step selectively removes undesirable information from the model, and the relearning step reinforces features that are consistently useful under different conditions. The forget-and-relearn framework unifies many existing iterative training algorithms in the image classification and language emergence literature, and allows us to understand the success of these algorithms in terms of the disproportionate forgetting of undesirable information. We leverage this understanding to improve upon existing algorithms by designing more targeted forgetting operations. Insights from our analysis provide a coherent view on the dynamics of iterative training in neural networks and offer a clear path towards performance improvements.","url_abs":"https://arxiv.org/abs/2202.00155v1","url_pdf":"https://arxiv.org/pdf/2202.00155v1.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":"fortuitous-forgetting-in-connectionist-1","repo_url":"https://github.com/hlml/fortuitous_forgetting","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2202.00155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.00155"}},"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/hlml/fortuitous_forgetting","reach":null}],"summary":{"ran_fixture":1,"ran_draft_wrong":3,"ran_honours":2},"by_repo_kind":{"official":{"samples":6,"ran":6,"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":6,"samples":[{"code_sha256_prefix":"badd0c4bc44d8a29","entry":"convert_data_to_tensor","repo":"hlml/fortuitous_forgetting","repo_kind":"official","path":"ease_of_teaching/forget_train.py","file_url":"https://github.com/hlml/fortuitous_forgetting/blob/HEAD/ease_of_teaching/forget_train.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"badd0c4bc44d8a29"}},{"code_sha256_prefix":"13e0b35909c0dfbc","entry":"get_trainer","repo":"hlml/fortuitous_forgetting","repo_kind":"official","path":"llf_ke/train_KE_cls.py","file_url":"https://github.com/hlml/fortuitous_forgetting/blob/HEAD/llf_ke/train_KE_cls.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":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"13e0b35909c0dfbc"}},{"code_sha256_prefix":"c3d99cad036fdd02","entry":"load_datasets","repo":"hlml/fortuitous_forgetting","repo_kind":"official","path":"targeted_forgetting/mixed_group_training.py","file_url":"https://github.com/hlml/fortuitous_forgetting/blob/HEAD/targeted_forgetting/mixed_group_training.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c3d99cad036fdd02"}},{"code_sha256_prefix":"47ff0bc895e6393d","entry":"save_weight_one_iter","repo":"hlml/fortuitous_forgetting","repo_kind":"official","path":"ease_of_teaching/forget_train.py","file_url":"https://github.com/hlml/fortuitous_forgetting/blob/HEAD/ease_of_teaching/forget_train.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"47ff0bc895e6393d"}},{"code_sha256_prefix":"be30a111de94186a","entry":"test","repo":"hlml/fortuitous_forgetting","repo_kind":"official","path":"targeted_forgetting/mixed_group_training.py","file_url":"https://github.com/hlml/fortuitous_forgetting/blob/HEAD/targeted_forgetting/mixed_group_training.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be30a111de94186a"}},{"code_sha256_prefix":"dfdc385882e7d348","entry":"torch_bernoulli","repo":"hlml/fortuitous_forgetting","repo_kind":"official","path":"targeted_forgetting/mixed_group_training.py","file_url":"https://github.com/hlml/fortuitous_forgetting/blob/HEAD/targeted_forgetting/mixed_group_training.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dfdc385882e7d348"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}