{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:05:57Z","timestamp":1792688757108,"version":"4.5.0"},"reference-count":52,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T00:00:00Z","timestamp":1708560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100011688","name":"ECSEL Joint Undertaking","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100011688","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2024,4,30]]},"abstract":"<jats:p>\n                    Federated Learning (FL) is a distributed machine learning paradigm that enables learning models from decentralized private datasets where the labeling effort is entrusted to the clients. While most existing FL approaches assume high-quality labels are readily available on users\u2019 devices, in reality, label noise can naturally occur in FL and is closely related to clients\u2019 characteristics. Due to scarcity of available data and significant label noise variations among clients in FL, existing state-of-the-art centralized approaches exhibit unsatisfactory performance, whereas prior FL studies rely on excessive on-device computational schemes or additional clean data available on the server. We propose\u00a0\n                    <jats:monospace>FedLN<\/jats:monospace>\n                    , a framework to deal with label noise across different FL training stages, namely FL initialization, on-device model training, and server model aggregation, able to accommodate the diverse computational capabilities of devices in an FL system. Specifically,\u00a0\n                    <jats:monospace>FedLN<\/jats:monospace>\n                    \u00a0computes per-client noise level estimation in a single federated round and improves the models\u2019 performance by either correcting or mitigating the effect of noisy samples. Our evaluation on various publicly available vision and audio datasets demonstrates a 22% improvement on average compared to other existing methods for a label noise level of 60%. We further validate the efficiency of\u00a0\n                    <jats:monospace>FedLN<\/jats:monospace>\n                    \u00a0in human-annotated real-world noisy datasets and report a 4.8% increase on average in models\u2019 recognition performance, highlighting that\u00a0\n                    <jats:monospace>FedLN<\/jats:monospace>\n                    \u00a0can be useful for improving FL services provided to everyday users.\n                  <\/jats:p>","DOI":"10.1145\/3626242","type":"journal-article","created":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T08:17:27Z","timestamp":1696839447000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":40,"title":["Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels"],"prefix":"10.1145","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9143-1188","authenticated-orcid":false,"given":"Vasileios","family":"Tsouvalas","sequence":"first","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1473-0322","authenticated-orcid":false,"given":"Aaqib","family":"Saeed","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7092-5998","authenticated-orcid":false,"given":"Tanir","family":"Ozcelebi","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8379-770X","authenticated-orcid":false,"given":"Nirvana","family":"Meratnia","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology, Eindhoven, The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,2,22]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","unstructured":"Ehsan Amid Manfred K. Warmuth Rohan Anil and Tomer Koren. 2019. Robust bi-tempered logistic loss based on Bregman divergences. arXiv:1906.03361 (2019). 10.48550\/ARXIV.1906.03361","DOI":"10.48550\/ARXIV.1906.03361"},{"key":"e_1_3_3_3_2","unstructured":"Eric Arazo Diego Ortego Paul Albert Noel E. O\u2019Connor and Kevin McGuinness. 2019. Unsupervised label noise modeling and loss correction. arXiv:cs.CV\/1904.11238 (2019)."},{"key":"e_1_3_3_4_2","first-page":"233","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Arpit Devansh","year":"2017","unstructured":"Devansh Arpit, Stanis\u0142aw Jastrz\u0119bski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S. Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, and Simon Lacoste-Julien. 2017. A closer look at memorization in deep networks. In Proceedings of the International Conference on Machine Learning. 233\u2013242."},{"key":"e_1_3_3_5_2","volume-title":"Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS \u201921)","author":"Bai Yingbin","year":"2021","unstructured":"Yingbin Bai, Erkun Yang, Bo Han, Yanhua Yang, Jiatong Li, Yinian Mao, Gang Niu, and Tongliang Liu. 2021. Understanding and improving early stopping for learning with noisy labels. In Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS \u201921). 1\u201312."},{"key":"e_1_3_3_6_2","article-title":"Flower: A friendly federated learning research framework","author":"Beutel Daniel J.","year":"2020","unstructured":"Daniel J. Beutel, Taner Topal, Akhil Mathur, Xinchi Qiu, Titouan Parcollet, and Nicholas D. Lane. 2020. Flower: A friendly federated learning research framework. arXiv preprint arXiv:2007.14390 (2020).","journal-title":"arXiv preprint arXiv:2007.14390"},{"key":"e_1_3_3_7_2","doi-asserted-by":"crossref","unstructured":"Yiqiang Chen Xiaodong Yang Xin Qin Han Yu Biao Chen and Zhiqi Shen. 2020. FOCUS: Dealing with label quality disparity in federated learning. arXiv:cs.LG\/2001.11359 (2020).","DOI":"10.1007\/978-3-030-63076-8_8"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","unstructured":"Terrance DeVries and Graham W. Taylor. 2017. Improved regularization of convolutional neural networks with cutout. arXiv:1708.04552 (2017). 10.48550\/ARXIV.1708.04552","DOI":"10.48550\/ARXIV.1708.04552"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2022.07.013"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00983"},{"key":"e_1_3_3_11_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations: Conference Track (ICLR \u201917)","author":"Goldberger Jacob","year":"2017","unstructured":"Jacob Goldberger and Ehud Ben-Reuven. 2017. Training deep neural-networks using a noise adaptation layer. In Proceedings of the 5th International Conference on Learning Representations: Conference Track (ICLR \u201917)."},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","unstructured":"Chuan Guo Geoff Pleiss Yu Sun and Kilian Q. Weinberger. 2017. On calibration of modern neural networks. arXiv:1706.04599 (2017). 10.48550\/ARXIV.1706.04599","DOI":"10.48550\/ARXIV.1706.04599"},{"key":"e_1_3_3_13_2","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep residual learning for image recognition. arXiv:1512.03385 (2015). https:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2018.8519248"},{"key":"e_1_3_3_15_2","volume-title":"Advances in Neural Information Processing Systems","author":"Hendrycks Dan","year":"2018","unstructured":"Dan Hendrycks, Mantas Mazeika, Duncan Wilson, and Kevin Gimpel. 2018. Using trusted data to train deep networks on labels corrupted by severe noise. In Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi, and R. Garnett (Eds.), Vol. 31. Curran Associates.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2018\/file\/ad554d8c3b06d6b97ee76a2448bd7913-Paper.pdf"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv:1503.02531 (2015). 10.48550\/ARXIV.1503.02531","DOI":"10.48550\/ARXIV.1503.02531"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW.2013.139"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"e_1_3_3_19_2","volume-title":"Proceedings of the NIPS Workshop on Private Multi-Party Machine Learning","author":"Kone\u010dn\u00fd Jakub","year":"2016","unstructured":"Jakub Kone\u010dn\u00fd, H. Brendan McMahan, Felix X. Yu, Peter Richtarik, Ananda Theertha Suresh, and Dave Bacon. 2016. Federated learning: Strategies for improving communication efficiency. In Proceedings of the NIPS Workshop on Private Multi-Party Machine Learning. https:\/\/arxiv.org\/abs\/1610.05492"},{"key":"e_1_3_3_20_2","volume-title":"Learning Multiple Layers of Features from Tiny Images","author":"Krizhevsky Alex","year":"2009","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. Technical Report. University of Toronto."},{"key":"e_1_3_3_21_2","doi-asserted-by":"crossref","unstructured":"David Leroy Alice Coucke Thibaut Lavril Thibault Gisselbrecht and Joseph Dureau. 2019. Federated learning for keyword spotting. arXiv:eess.AS\/1810.05512 (2019).","DOI":"10.1109\/ICASSP.2019.8683546"},{"key":"e_1_3_3_22_2","first-page":"4313","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Li Mingchen","year":"2020","unstructured":"Mingchen Li, Mahdi Soltanolkotabi, and Samet Oymak. 2020. Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks. In Proceedings of the International Conference on Artificial Intelligence and Statistics. 4313\u20134324."},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","unstructured":"Weitang Liu Xiaoyun Wang John D. Owens and Yixuan Li. 2020. Energy-based out-of-distribution detection. arXiv:2010.03759 (2020). 10.48550\/ARXIV.2010.03759","DOI":"10.48550\/ARXIV.2010.03759"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","unstructured":"Michal Lukasik Srinadh Bhojanapalli Aditya Krishna Menon and Sanjiv Kumar. 2020. Does label smoothing mitigate label noise? arXiv:2003.02819 (2020). 10.48550\/ARXIV.2003.02819","DOI":"10.48550\/ARXIV.2003.02819"},{"key":"e_1_3_3_26_2","first-page":"1273","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. 1273\u20131282."},{"key":"e_1_3_3_27_2","unstructured":"Rafael M\u00fcller Simon Kornblith and Geoffrey Hinton. 2020. When does label smoothing help? arXiv:cs.LG\/1906.02629 (2020)."},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","unstructured":"Curtis G. Northcutt Lu Jiang and Isaac L. Chuang. 2019. Confident learning: Estimating uncertainty in dataset labels. arXiv:1911.00068 (2019). 10.48550\/ARXIV.1911.00068","DOI":"10.48550\/ARXIV.1911.00068"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","unstructured":"Giorgio Patrini Alessandro Rozza Aditya Menon Richard Nock and Lizhen Qu. 2016. Making deep neural networks robust to label noise: A loss correction approach. arXiv:1609.03683 (2016). 10.48550\/ARXIV.1609.03683","DOI":"10.48550\/ARXIV.1609.03683"},{"key":"e_1_3_3_30_2","first-page":"8748","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In Proceedings of the International Conference on Machine Learning. 8748\u20138763."},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157797"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","unstructured":"Adriana Romero Nicolas Ballas Samira Ebrahimi Kahou Antoine Chassang Carlo Gatta and Yoshua Bengio. 2014. FitNets: Hints for thin deep nets. arXiv:1412.6550 (2014). 10.48550\/ARXIV.1412.6550","DOI":"10.48550\/ARXIV.1412.6550"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"e_1_3_3_34_2","article-title":"TRILLsson: Distilled universal paralinguistic speech representations","author":"Shor Joel","year":"2022","unstructured":"Joel Shor and Subhashini Venugopalan. 2022. TRILLsson: Distilled universal paralinguistic speech representations. arXiv preprint arXiv:2203.00236 (2022).","journal-title":"arXiv preprint arXiv:2203.00236"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","unstructured":"Hwanjun Song Minseok Kim Dongmin Park Yooju Shin and Jae-Gil Lee. 2020. Learning from noisy labels with deep neural networks: A survey. arXiv:2007.08199 (2020). 10.48550\/ARXIV.2007.08199","DOI":"10.48550\/ARXIV.2007.08199"},{"key":"e_1_3_3_36_2","article-title":"Self-supervised audio representation learning for mobile devices","author":"Tagliasacchi Marco","year":"2019","unstructured":"Marco Tagliasacchi, Beat Gfeller, F\u00e9lix de Chaumont Quitry, and Dominik Roblek. 2019. Self-supervised audio representation learning for mobile devices. arXiv preprint arXiv:1905.11796 (2019).","journal-title":"arXiv preprint arXiv:1905.11796"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475622"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","unstructured":"Asher Trockman and J. Zico Kolter. 2022. Patches are all you need? arXiv:2201.09792 (2022). 10.48550\/ARXIV.2201.09792","DOI":"10.48550\/ARXIV.2201.09792"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3520128"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"e_1_3_3_41_2","unstructured":"P. Warden. 2018. Speech Commands: A dataset for limited-vocabulary speech recognition. arXiv e-prints arXiv:cs.CL\/1804.03209 (2018)."},{"key":"e_1_3_3_42_2","article-title":"Learning with noisy labels revisited: A study using real-world human annotations","volume":"2110","author":"Wei Jiaheng","year":"2021","unstructured":"Jiaheng Wei, Zhaowei Zhu, Hao Cheng, Tongliang Liu, Gang Niu, and Yang Liu. 2021. Learning with noisy labels revisited: A study using real-world human annotations. CoRR abs\/2110.12088 (2021).","journal-title":"CoRR"},{"key":"e_1_3_3_43_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Xia Xiaobo","year":"2021","unstructured":"Xiaobo Xia, Tongliang Liu, Bo Han, Chen Gong, Nannan Wang, Zongyuan Ge, and Yi Chang. 2021. Robust early-learning: Hindering the memorization of noisy labels. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_44_2","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","volume":"1708","author":"Xiao Han","year":"2017","unstructured":"Han Xiao, Kashif Rasul, and Roland Vollgraf. 2017. Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms. CoRR abs\/1708.07747 (2017).","journal-title":"CoRR"},{"key":"e_1_3_3_45_2","unstructured":"Jingyi Xu Zihan Chen Tony Q. S. Quek and Kai Fong Ernest Chong. 2022. FedCorr: Multi-stage federated learning for label noise correction. arXiv:cs.LG\/2204.04677 (2022)."},{"key":"e_1_3_3_46_2","doi-asserted-by":"crossref","unstructured":"Jiancheng Yang Rui Shi Donglai Wei Zequan Liu Lin Zhao Bilian Ke Hanspeter Pfister and Bingbing Ni. 2023. MedMNIST v2: A large-scale lightweight benchmark for 2D and 3D biomedical image classification. Scientific Data 10 (2023) 41.","DOI":"10.1038\/s41597-022-01721-8"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3131852"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/mis.2022.3151466"},{"key":"e_1_3_3_49_2","unstructured":"Timothy Yang Galen Andrew Hubert Eichner Haicheng Sun Wei Li Nicholas Kong Daniel Ramage and Fran\u00e7oise Beaufays. 2018. Applied federated learning: Improving Google keyboard query suggestions. arXiv:cs.LG\/1812.02903 (2018)."},{"key":"e_1_3_3_50_2","doi-asserted-by":"publisher","unstructured":"Bixiao Zeng Xiaodong Yang Yiqiang Chen Hanchao Yu and Yingwei Zhang. 2022. CLC: A consensus-based label correction approach in federated learning. ACM Transactions on Intelligent Systems and Technology 13 5 (June 2022) Article 75 23 pages. 10.1145\/3519311","DOI":"10.1145\/3519311"},{"key":"e_1_3_3_51_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, and David Lopez-Paz. 2018. Mixup: Beyond empirical risk minimization. In Proceedings of the International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=r1Ddp1-Rb"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3591363"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","unstructured":"Zhaowei Zhu Zihao Dong and Yang Liu. 2021. Detecting corrupted labels without training a model to predict. arXiv:2110.06283 (2021). 10.48550\/ARXIV.2110.06283","DOI":"10.48550\/ARXIV.2110.06283"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626242","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626242","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:05:47Z","timestamp":1750277147000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626242"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,22]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4,30]]}},"alternative-id":["10.1145\/3626242"],"URL":"https:\/\/doi.org\/10.1145\/3626242","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,22]]},"assertion":[{"value":"2022-10-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-08-15","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}