{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:09:23Z","timestamp":1753884563351,"version":"3.41.2"},"reference-count":36,"publisher":"World Scientific Pub Co Pte Ltd","issue":"05","funder":[{"name":"the Science Research Project of Anhui Higher Education Institutions","award":["2023AH050914"],"award-info":[{"award-number":["2023AH050914"]}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61902001"],"award-info":[{"award-number":["61902001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Science and Technology Project of Wuhu City","award":["2023pt07","2023ly13"],"award-info":[{"award-number":["2023pt07","2023ly13"]}]},{"name":"the Quality Engineering Project of Anhui Higher Education Institutions","award":["2023zybj018"],"award-info":[{"award-number":["2023zybj018"]}]},{"name":"the Quality Improvement Program of Anhui Polytechnic University","award":["2022lzyybj02"],"award-info":[{"award-number":["2022lzyybj02"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J CIRCUIT SYST COMP"],"published-print":{"date-parts":[[2025,3,30]]},"abstract":"<jats:p> End-cloud collaborative computing framework ensures the security and privacy of edge device data, enabling collaborative training of global models without direct data exchange. However, in practical scenarios, anomalies in training or edge device data may severely degrade or disable the global model\u2019s performance. Existing frameworks lack effective debugging and anomaly localization, hindering real-time monitoring and precise identification of abnormal edge devices in data heterogeneity scenarios. In this paper, we propose a new method named FedCheck, a debugging framework for end-cloud collaborative federated learning that enables real-time alerts and detects abnormal devices for nonindependent and identically distributed (nonIID) data without disrupting the regular training process. Specifically, we employ a model similarity-based method to quantitatively assess the degree of device anomaly in data heterogeneity scenarios, supporting real-time alerts during the end-cloud collaboration process. Furthermore, a simulation program replays the training process based on recorded telemetry data, facilitating backtracking debugging of any training round and the status of edge devices. Finally, the framework removes abnormal devices and repairs the global model. Experiments on MNIST and Fashion-MNIST datasets demonstrate that FedCheck can effectively detect and locate abnormal devices in data heterogeneity scenarios. Even in large-scale federated learning, it maintains high detection performance and exhibits good scalability. <\/jats:p>","DOI":"10.1142\/s0218126625501117","type":"journal-article","created":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T10:26:32Z","timestamp":1728037592000},"source":"Crossref","is-referenced-by-count":0,"title":["An End-Cloud Collaborative Federated Learning Debugging Framework for Data Heterogeneity"],"prefix":"10.1142","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4671-9825","authenticated-orcid":false,"given":"Chao","family":"Kong","sequence":"first","affiliation":[{"name":"School of Computer and Information, Anhui Polytechnic University, Wuhu 241000, P.\u00a0R.\u00a0China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1980-9283","authenticated-orcid":false,"given":"Dan","family":"Meng","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Shenzhen 518000, P.\u00a0R.\u00a0China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3512-9656","authenticated-orcid":false,"given":"Zhihui","family":"Fu","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Shenzhen 518000, P.\u00a0R.\u00a0China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0247-7998","authenticated-orcid":false,"given":"Ruiguang","family":"Pei","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Shenzhen 518000, P.\u00a0R.\u00a0China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3997-2282","authenticated-orcid":false,"given":"Junjie","family":"Wu","sequence":"additional","affiliation":[{"name":"OPPO Research Institute, Shenzhen 518000, P.\u00a0R.\u00a0China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0504-0997","authenticated-orcid":false,"given":"Haibei","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta 30332, USA"}]},{"given":"Tong","family":"Zhan","sequence":"additional","affiliation":[{"name":"Salesforce TMP Org, San Francisco 94105, USA"}]}],"member":"219","published-online":{"date-parts":[[2024,12,23]]},"reference":[{"key":"S0218126625501117BIB001","first-page":"1057","volume":"33","author":"Liu Y.","year":"2022","journal-title":"Ruan Jian Xue Bao\/J. Softw."},{"key":"S0218126625501117BIB002","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04065-3"},{"key":"S0218126625501117BIB003","doi-asserted-by":"publisher","DOI":"10.1145\/3339474"},{"key":"S0218126625501117BIB004","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3333914"},{"key":"S0218126625501117BIB005","doi-asserted-by":"publisher","DOI":"10.1145\/3514500"},{"key":"S0218126625501117BIB006","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2991401"},{"key":"S0218126625501117BIB007","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19993"},{"key":"S0218126625501117BIB008","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-022-01647-y"},{"key":"S0218126625501117BIB009","first-page":"312","volume-title":"Int. Conf. Machine Learning","author":"Arazo E.","year":"2019"},{"key":"S0218126625501117BIB010","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE48307.2020.00047"},{"key":"S0218126625501117BIB011","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3137321"},{"key":"S0218126625501117BIB012","doi-asserted-by":"publisher","DOI":"10.1109\/ICOIN56518.2023.10048907"},{"key":"S0218126625501117BIB013","first-page":"1346","volume":"60","author":"Guo S.","year":"2023","journal-title":"J. Comput. Res. Develop."},{"key":"S0218126625501117BIB014","doi-asserted-by":"publisher","DOI":"10.1142\/S0218126622503145"},{"key":"S0218126625501117BIB015","first-page":"824","volume":"33","author":"Zhou P.","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"S0218126625501117BIB016","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3376548"},{"key":"S0218126625501117BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3110743"},{"key":"S0218126625501117BIB018","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3205551"},{"key":"S0218126625501117BIB019","doi-asserted-by":"publisher","DOI":"10.1145\/3236024.3236082"},{"key":"S0218126625501117BIB020","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380423"},{"key":"S0218126625501117BIB021","doi-asserted-by":"publisher","DOI":"10.1145\/3426866"},{"key":"S0218126625501117BIB022","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539231"},{"key":"S0218126625501117BIB023","first-page":"6893","volume-title":"Proc. 36th Int. Conf. Machine Learning","author":"Xie C.","year":"2019"},{"key":"S0218126625501117BIB024","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24434"},{"key":"S0218126625501117BIB025","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/5968168"},{"key":"S0218126625501117BIB026","first-page":"301","volume-title":"Proc. 23rd Int. Symp. Research in Attacks, Intrusions and Defenses","author":"Fung C.","year":"2020"},{"key":"S0218126625501117BIB027","first-page":"894","volume":"45","author":"Cai H.","year":"2023","journal-title":"J. Electron. Inf. Technol."},{"key":"S0218126625501117BIB028","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00053"},{"key":"S0218126625501117BIB029","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29078"},{"key":"S0218126625501117BIB030","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072491"},{"key":"S0218126625501117BIB031","first-page":"3257","volume-title":"Proc. 2019 Conf. North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Saphra N.","year":"2019"},{"key":"S0218126625501117BIB032","first-page":"5732","volume-title":"Proc. 32rd Conf. Neural Information Processing Systems","author":"Morcos A. S.","year":"2018"},{"key":"S0218126625501117BIB033","first-page":"3519","volume-title":"Proc. 36th Int. Conf. Machine Learning","author":"Kornblith S.","year":"2019"},{"key":"S0218126625501117BIB034","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.10.005"},{"key":"S0218126625501117BIB035","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3196503"},{"key":"S0218126625501117BIB036","first-page":"1273","volume-title":"Proc. 20th Int. Conf. on Artificial Intelligence and Statistics","author":"McMahan B.","year":"2017"}],"container-title":["Journal of Circuits, Systems and Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218126625501117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T09:07:43Z","timestamp":1743584863000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218126625501117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,23]]},"references-count":36,"journal-issue":{"issue":"05","published-print":{"date-parts":[[2025,3,30]]}},"alternative-id":["10.1142\/S0218126625501117"],"URL":"https:\/\/doi.org\/10.1142\/s0218126625501117","relation":{},"ISSN":["0218-1266","1793-6454"],"issn-type":[{"type":"print","value":"0218-1266"},{"type":"electronic","value":"1793-6454"}],"subject":[],"published":{"date-parts":[[2024,12,23]]},"article-number":"2550111"}}