{"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/knowledge-accumulation-in-continually-learned","title":"Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting","arxiv_id":"2304.00933","date":"2023-04-03","proceeding":null,"authors":["Timm Hess","Eli Verwimp","Gido M. van de Ven","Tinne Tuytelaars"],"abstract":"Continual learning research has shown that neural networks suffer from catastrophic forgetting \"at the output level\", but it is debated whether this is also the case at the level of learned representations. Multiple recent studies ascribe representations a certain level of innate robustness against forgetting -- that they only forget minimally in comparison with forgetting at the output level. We revisit and expand upon the experiments that revealed this difference in forgetting and illustrate the coexistence of two phenomena that affect the quality of continually learned representations: knowledge accumulation and feature forgetting. Taking both aspects into account, we show that, even though forgetting in the representation (i.e. feature forgetting) can be small in absolute terms, when measuring relative to how much was learned during a task, forgetting in the representation tends to be just as catastrophic as forgetting at the output level. Next we show that this feature forgetting is problematic as it substantially slows down the incremental learning of good general representations (i.e. knowledge accumulation). Finally, we study how feature forgetting and knowledge accumulation are affected by different types of continual learning methods.","url_abs":"https://arxiv.org/abs/2304.00933v4","url_pdf":"https://arxiv.org/pdf/2304.00933v4.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":"knowledge-accumulation-in-continually-learned","repo_url":"https://github.com/timmhess/kaaff","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.00933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.00933"}},"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/timmhess/kaaff","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"4a3907baf03af341","entry":"batch_norm","repo":"timmhess/kaaff","repo_kind":"official","path":"avalanche/models/icarl_resnet.py","file_url":"https://github.com/timmhess/kaaff/blob/HEAD/avalanche/models/icarl_resnet.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":"4a3907baf03af341"}},{"code_sha256_prefix":"f522c857bf857a12","entry":"conv3x3","repo":"timmhess/kaaff","repo_kind":"official","path":"avalanche/models/icarl_resnet.py","file_url":"https://github.com/timmhess/kaaff/blob/HEAD/avalanche/models/icarl_resnet.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":"f522c857bf857a12"}},{"code_sha256_prefix":"dbea80a99c4d5fb4","entry":"get_feat_size","repo":"timmhess/kaaff","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/timmhess/kaaff/blob/HEAD/src/model.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":"dbea80a99c4d5fb4"}},{"code_sha256_prefix":"7c38a66591845c21","entry":"get_grad_normL2","repo":"timmhess/kaaff","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/timmhess/kaaff/blob/HEAD/src/utils.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":"7c38a66591845c21"}},{"code_sha256_prefix":"bd1906e457add957","entry":"get_transforms","repo":"timmhess/kaaff","repo_kind":"official","path":"helper.py","file_url":"https://github.com/timmhess/kaaff/blob/HEAD/helper.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":"bd1906e457add957"}},{"code_sha256_prefix":"6631136159e03f28","entry":"make_icarl_net","repo":"timmhess/kaaff","repo_kind":"official","path":"avalanche/models/icarl_resnet.py","file_url":"https://github.com/timmhess/kaaff/blob/HEAD/avalanche/models/icarl_resnet.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":"6631136159e03f28"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}