{"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/federated-learning-with-label-distribution","title":"Federated Learning with Label Distribution Skew via Logits Calibration","arxiv_id":"2209.00189","date":"2022-09-01","proceeding":null,"authors":["Jie Zhang","Zhiqi Li","Bo Li","Jianghe Xu","Shuang Wu","Shouhong Ding","Chao Wu"],"abstract":"Traditional federated optimization methods perform poorly with heterogeneous data (ie, accuracy reduction), especially for highly skewed data. In this paper, we investigate the label distribution skew in FL, where the distribution of labels varies across clients. First, we investigate the label distribution skew from a statistical view. We demonstrate both theoretically and empirically that previous methods based on softmax cross-entropy are not suitable, which can result in local models heavily overfitting to minority classes and missing classes. Additionally, we theoretically introduce a deviation bound to measure the deviation of the gradient after local update. At last, we propose FedLC (\\textbf {Fed} erated learning via\\textbf {L} ogits\\textbf {C} alibration), which calibrates the logits before softmax cross-entropy according to the probability of occurrence of each class. FedLC applies a fine-grained calibrated cross-entropy loss to local update by adding a pairwise label margin. Extensive experiments on federated datasets and real-world datasets demonstrate that FedLC leads to a more accurate global model and much improved performance. Furthermore, integrating other FL methods into our approach can further enhance the performance of the global model.","url_abs":"https://arxiv.org/abs/2209.00189v2","url_pdf":"https://arxiv.org/pdf/2209.00189v2.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":"federated-learning-with-label-distribution","repo_url":"https://github.com/KarhouTam/FL-bench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"federated-learning-with-label-distribution","repo_url":"https://github.com/bytedance/feddecorr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"federated-learning-with-label-distribution","repo_url":"https://github.com/thejungwon/gc-fed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.00189","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.00189"}},"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/thejungwon/gc-fed","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/KarhouTam/FL-bench","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bytedance/feddecorr","reach":null}],"summary":{"ran":3,"ran_fixture":1,"unverified":1},"by_repo_kind":{"listed":{"samples":5,"ran":4,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"af8f3034a8ca7b6f","entry":"FedAvg","repo":"bytedance/feddecorr","repo_kind":"listed","path":"approach/fedlogitcal.py","file_url":"https://github.com/bytedance/feddecorr/blob/HEAD/approach/fedlogitcal.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"af8f3034a8ca7b6f"}},{"code_sha256_prefix":"f64d951d32b9b6d8","entry":"FedDecorrLoss","repo":"bytedance/feddecorr","repo_kind":"listed","path":"approach/fedlogitcal.py","file_url":"https://github.com/bytedance/feddecorr/blob/HEAD/approach/fedlogitcal.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f64d951d32b9b6d8"}},{"code_sha256_prefix":"1c10c22b09b2f3ce","entry":"FedLogitCal","repo":"bytedance/feddecorr","repo_kind":"listed","path":"approach/fedlogitcal.py","file_url":"https://github.com/bytedance/feddecorr/blob/HEAD/approach/fedlogitcal.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1c10c22b09b2f3ce"}},{"code_sha256_prefix":"e7e5bb878fd22400","entry":"compute_accuracy","repo":"bytedance/feddecorr","repo_kind":"listed","path":"approach/fedlogitcal.py","file_url":"https://github.com/bytedance/feddecorr/blob/HEAD/approach/fedlogitcal.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7e5bb878fd22400"}},{"code_sha256_prefix":"6c35df54afa9cd25","entry":"FedLCClient","repo":"thejungwon/gc-fed","repo_kind":"listed","path":"algorithms/fedlc.py","file_url":"https://github.com/thejungwon/gc-fed/blob/HEAD/algorithms/fedlc.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":"6c35df54afa9cd25"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}