{"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/task-confusion-and-catastrophic-forgetting-in","title":"Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings","arxiv_id":"2410.20768","date":"2024-10-28","proceeding":null,"authors":["Milad Khademi Nori","Il-Min Kim"],"abstract":"In class-incremental learning (class-IL), models must classify all previously seen classes at test time without task-IDs, leading to task confusion. Despite being a key challenge, task confusion lacks a theoretical understanding. We present a novel mathematical framework for class-IL and prove the Infeasibility Theorem, showing optimal class-IL is impossible with discriminative modeling due to task confusion. However, we establish the Feasibility Theorem, demonstrating that generative modeling can achieve optimal class-IL by overcoming task confusion. We then assess popular class-IL strategies, including regularization, bias-correction, replay, and generative classifier, using our framework. Our analysis suggests that adopting generative modeling, either for generative replay or direct classification (generative classifier), is essential for optimal class-IL.","url_abs":"https://arxiv.org/abs/2410.20768v1","url_pdf":"https://arxiv.org/pdf/2410.20768v1.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":"task-confusion-and-catastrophic-forgetting-in","repo_url":"https://github.com/miladkhademinori/class-incremental-learning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"class-incremental-learning","task_name":"Class Incremental Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"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=2410.20768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20768"}},"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":"deterministic:regex_extraction","url":"https://github.com/miladkhademinori/class-incremental-learning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":"63de4565a29c4d49","entry":"define_autoencoder","repo":"miladkhademinori/class-incremental-learning","repo_kind":"official","path":"define_models.py","file_url":"https://github.com/miladkhademinori/class-incremental-learning/blob/HEAD/define_models.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":"63de4565a29c4d49"}},{"code_sha256_prefix":"247e38928eef8da6","entry":"download","repo":"miladkhademinori/class-incremental-learning","repo_kind":"official","path":"preprocess_core50.py","file_url":"https://github.com/miladkhademinori/class-incremental-learning/blob/HEAD/preprocess_core50.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":"247e38928eef8da6"}},{"code_sha256_prefix":"8fcb2c95a6a3d03e","entry":"get_data_loader","repo":"miladkhademinori/class-incremental-learning","repo_kind":"official","path":"preprocess_core50.py","file_url":"https://github.com/miladkhademinori/class-incremental-learning/blob/HEAD/preprocess_core50.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":"8fcb2c95a6a3d03e"}},{"code_sha256_prefix":"2bcd75034219597d","entry":"label_squeezing_collate_fn","repo":"miladkhademinori/class-incremental-learning","repo_kind":"official","path":"preprocess_core50.py","file_url":"https://github.com/miladkhademinori/class-incremental-learning/blob/HEAD/preprocess_core50.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":"2bcd75034219597d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}