{"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/no-one-left-behind-real-world-federated-class","title":"No One Left Behind: Real-World Federated Class-Incremental Learning","arxiv_id":"2302.00903","date":"2023-02-02","proceeding":null,"authors":["Jiahua Dong","Hongliu Li","Yang Cong","Gan Sun","Yulun Zhang","Luc van Gool"],"abstract":"Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data categories of FL framework are known and fixed in advance. Moreover, some new local clients that collect novel categories unseen by other clients may be introduced to FL training irregularly. These issues render global model to undergo catastrophic forgetting on old categories, when local clients receive new categories consecutively under limited memory of storing old categories. To tackle the above issues, we propose a novel Local-Global Anti-forgetting (LGA) model. It ensures no local clients are left behind as they learn new classes continually, by addressing local and global catastrophic forgetting. Specifically, considering tackling class imbalance of local client to surmount local forgetting, we develop a category-balanced gradient-adaptive compensation loss and a category gradient-induced semantic distillation loss. They can balance heterogeneous forgetting speeds of hard-to-forget and easy-to-forget old categories, while ensure consistent class-relations within different tasks. Moreover, a proxy server is designed to tackle global forgetting caused by Non-IID class imbalance between different clients. It augments perturbed prototype images of new categories collected from local clients via self-supervised prototype augmentation, thus improving robustness to choose the best old global model for local-side semantic distillation loss. Experiments on representative datasets verify superior performance of our model against comparison methods. The code is available at https://github.com/JiahuaDong/LGA.","url_abs":"https://arxiv.org/abs/2302.00903v3","url_pdf":"https://arxiv.org/pdf/2302.00903v3.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":"no-one-left-behind-real-world-federated-class","repo_url":"https://github.com/jiahuadong/lga","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"no-one-left-behind-real-world-federated-class","repo_url":"https://github.com/jiahuadong/fiss","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":"federated-learning","task_name":"Federated 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":{"syntology_url":"https://syntology.ai/paper/2302.00903","atlas_url":"https://app.syntology.ai/?focus=2302.00903","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00903"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/jiahuadong/fiss","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jiahuadong/lga","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"code_sha256_prefix":"be3aa807c2960a0b","entry":"entropy","repo":"jiahuadong/lga","repo_kind":"official","path":"LGA.py","file_url":"https://github.com/jiahuadong/lga/blob/HEAD/LGA.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"be3aa807c2960a0b"}},{"code_sha256_prefix":"8248ed8af5d57be5","entry":"get_one_hot","repo":"jiahuadong/lga","repo_kind":"official","path":"LGA.py","file_url":"https://github.com/jiahuadong/lga/blob/HEAD/LGA.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8248ed8af5d57be5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}