{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T00:59:29Z","timestamp":1771981169434,"version":"3.50.1"},"reference-count":53,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2022,6,11]],"date-time":"2022-06-11T00:00:00Z","timestamp":1654905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"RGC Grant Research","award":["17203320"],"award-info":[{"award-number":["17203320"]}]},{"DOI":"10.13039\/501100004359","name":"Swedish Research Council","doi-asserted-by":"crossref","award":["2017-04543"],"award-info":[{"award-number":["2017-04543"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"crossref"}]},{"name":"European Union\u2019s Horizon 2020 research and innovation programme","award":["101015922"],"award-info":[{"award-number":["101015922"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2022,10,31]]},"abstract":"<jats:p>\n            Federated learning provides a communication-efficient and privacy-preserving training process by enabling learning statistical models with massive participants without accessing their local data. Standard federated learning techniques that naively minimize an average loss function are vulnerable to data corruptions from outliers, systematic mislabeling, or even adversaries. In this article, we address this challenge by proposing Auto-weighted Robust Federated Learning (\n            <jats:monospace>ARFL<\/jats:monospace>\n            ), a novel approach that jointly learns the global model and the weights of local updates to provide robustness against corrupted data sources. We prove a learning bound on the expected loss with respect to the predictor and the weights of clients, which guides the definition of the objective for robust federated learning. We present an objective that minimizes the weighted sum of empirical risk of clients with a regularization term, where the weights can be allocated by comparing the empirical risk of each client with the average empirical risk of the best\n            <jats:inline-formula content-type=\"math\/tex\">\n              <jats:tex-math notation=\"LaTeX\" version=\"MathJax\">\\( p \\)<\/jats:tex-math>\n            <\/jats:inline-formula>\n            clients. This method can downweight the clients with significantly higher losses, thereby lowering their contributions to the global model. We show that this approach achieves robustness when the data of corrupted clients is distributed differently from the benign ones. To optimize the objective function, we propose a communication-efficient algorithm based on the blockwise minimization paradigm. We conduct extensive experiments on multiple benchmark datasets, including CIFAR-10, FEMNIST, and Shakespeare, considering different neural network models. The results show that our solution is robust against different scenarios, including label shuffling, label flipping, and noisy features, and outperforms the state-of-the-art methods in most scenarios.\n          <\/jats:p>","DOI":"10.1145\/3517821","type":"journal-article","created":{"date-parts":[[2022,2,23]],"date-time":"2022-02-23T15:01:29Z","timestamp":1645628489000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["Auto-weighted Robust Federated Learning with Corrupted Data Sources"],"prefix":"10.1145","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0145-3127","authenticated-orcid":false,"given":"Shenghui","family":"Li","sequence":"first","affiliation":[{"name":"Uppsala University, Uppsala, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edith","family":"Ngai","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanghua","family":"Ye","sequence":"additional","affiliation":[{"name":"University College London, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thiemo","family":"Voigt","sequence":"additional","affiliation":[{"name":"Uppsala University and Research Institutes of Sweden (RISE), Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,6,11]]},"reference":[{"key":"e_1_3_5_2_2","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et\u00a0al. 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016).","journal-title":"arXiv preprint arXiv:1603.04467"},{"key":"e_1_3_5_3_2","first-page":"634","volume-title":"International Conference on Machine Learning","author":"Bhagoji Arjun Nitin","year":"2019","unstructured":"Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal, and Seraphin Calo. 2019. Analyzing federated learning through an adversarial lens. In International Conference on Machine Learning. PMLR, 634\u2013643."},{"key":"e_1_3_5_4_2","first-page":"119","volume-title":"Conference on Advances in Neural Information Processing Systems","author":"Blanchard Peva","year":"2017","unstructured":"Peva Blanchard, Rachid Guerraoui, Julien Stainer, et\u00a0al. 2017. Machine learning with adversaries: Byzantine tolerant gradient descent. In Conference on Advances in Neural Information Processing Systems. 119\u2013129."},{"key":"e_1_3_5_5_2","first-page":"169","volume-title":"Summer School on Machine Learning","author":"Bousquet Olivier","year":"2003","unstructured":"Olivier Bousquet, St\u00e9phane Boucheron, and G\u00e1bor Lugosi. 2003. Introduction to statistical learning theory. In Summer School on Machine Learning. Springer, 169\u2013207."},{"key":"e_1_3_5_6_2","doi-asserted-by":"publisher","DOI":"10.5555\/993483"},{"key":"e_1_3_5_7_2","article-title":"Leaf: A benchmark for federated settings","author":"Caldas Sebastian","year":"2018","unstructured":"Sebastian Caldas, Peter Wu, Tian Li, Jakub Kone\u010dn\u1ef3, H. Brendan McMahan, Virginia Smith, and Ameet Talwalkar. 2018. Leaf: A benchmark for federated settings. arXiv preprint arXiv:1812.01097 (2018).","journal-title":"arXiv preprint arXiv:1812.01097"},{"key":"e_1_3_5_8_2","volume-title":"ISOC Network and Distributed System Security Symposium (NDSS)","author":"Cao Xiaoyu","year":"2021","unstructured":"Xiaoyu Cao, Minghong Fang, Jia Liu, and Neil Zhenqiang Gong. 2021. FLTrust: Byzantine-robust federated learning via trust bootstrapping. In ISOC Network and Distributed System Security Symposium (NDSS)."},{"key":"e_1_3_5_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1012"},{"issue":"2","key":"e_1_3_5_10_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3154503","article-title":"Distributed statistical machine learning in adversarial settings: Byzantine gradient descent","volume":"1","author":"Chen Yudong","year":"2017","unstructured":"Yudong Chen, Lili Su, and Jiaming Xu. 2017. Distributed statistical machine learning in adversarial settings: Byzantine gradient descent. Proc. ACM Measur. Anal. Comput. Syst. 1, 2 (2017), 1\u201325.","journal-title":"Proc. ACM Measur. Anal. Comput. Syst."},{"key":"e_1_3_5_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966217"},{"key":"e_1_3_5_12_2","first-page":"1605","volume-title":"29th USENIX Security Symposium (USENIX Security\u201920)","author":"Fang Minghong","year":"2020","unstructured":"Minghong Fang, Xiaoyu Cao, Jinyuan Jia, and Neil Gong. 2020. Local model poisoning attacks to byzantine-robust federated learning. In 29th USENIX Security Symposium (USENIX Security\u201920). 1605\u20131622."},{"key":"e_1_3_5_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(99)00074-7"},{"key":"e_1_3_5_14_2","first-page":"3521","volume-title":"International Conference on Machine Learning","author":"Guerraoui Rachid","year":"2018","unstructured":"Rachid Guerraoui, S\u00e9bastien Rouault, et\u00a0al. 2018. The hidden vulnerability of distributed learning in byzantium. In International Conference on Machine Learning. 3521\u20133530."},{"key":"e_1_3_5_15_2","article-title":"Training speech recognition models with federated learning: A quality\/cost framework","author":"Guliani Dhruv","year":"2020","unstructured":"Dhruv Guliani, Francoise Beaufays, and Giovanni Motta. 2020. Training speech recognition models with federated learning: A quality\/cost framework. arXiv preprint arXiv:2010.15965 (2020).","journal-title":"arXiv preprint arXiv:2010.15965"},{"key":"e_1_3_5_16_2","first-page":"3973","volume-title":"International Conference on Machine Learning","author":"Hamer Jenny","year":"2020","unstructured":"Jenny Hamer, Mehryar Mohri, and Ananda Theertha Suresh. 2020. FedBoost: A communication-efficient algorithm for federated learning. In International Conference on Machine Learning. PMLR, 3973\u20133983."},{"key":"e_1_3_5_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5826"},{"key":"e_1_3_5_18_2","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu Tzu-Ming Harry","year":"2019","unstructured":"Tzu-Ming Harry Hsu, Hang Qi, and Matthew Brown. 2019. Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint arXiv:1909.06335 (2019).","journal-title":"arXiv preprint arXiv:1909.06335"},{"key":"e_1_3_5_19_2","first-page":"5201","volume-title":"Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research)","volume":"139","author":"Kairouz Peter","year":"2021","unstructured":"Peter Kairouz, Ziyu Liu, and Thomas Steinke. 2021. The distributed discrete Gaussian mechanism for federated learning with secure aggregation. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research), Marina Meila and Tong Zhang (Eds.), Vol. 139. 5201\u20135212."},{"key":"e_1_3_5_20_2","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"Kone\u010dn\u1ef3 Jakub","year":"2016","unstructured":"Jakub Kone\u010dn\u1ef3, H. Brendan McMahan, Daniel Ramage, and Peter Richt\u00e1rik. 2016. Federated optimization: Distributed machine learning for on-device intelligence. arXiv preprint arXiv:1610.02527 (2016).","journal-title":"arXiv preprint arXiv:1610.02527"},{"key":"e_1_3_5_21_2","article-title":"Federated learning: Strategies for improving communication efficiency","author":"Kone\u010dn\u1ef3 Jakub","year":"2016","unstructured":"Jakub Kone\u010dn\u1ef3, H. Brendan McMahan, Felix X. Yu, Peter Richt\u00e1rik, Ananda Theertha Suresh, and Dave Bacon. 2016. Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492 (2016).","journal-title":"arXiv preprint arXiv:1610.05492"},{"key":"e_1_3_5_22_2","first-page":"3488","volume-title":"International Conference on Machine Learning","author":"Konstantinov Nikola","year":"2019","unstructured":"Nikola Konstantinov and Christoph Lampert. 2019. Robust learning from untrusted sources. In International Conference on Machine Learning. PMLR, 3488\u20133498."},{"key":"e_1_3_5_23_2","article-title":"Learning to detect malicious clients for robust federated learning","author":"Li Suyi","year":"2020","unstructured":"Suyi Li, Yong Cheng, Wei Wang, Yang Liu, and Tianjian Chen. 2020. Learning to detect malicious clients for robust federated learning. arXiv preprint arXiv:2002.00211 (2020).","journal-title":"arXiv preprint arXiv:2002.00211"},{"key":"e_1_3_5_24_2","article-title":"Federated multi-task learning for competing constraints","author":"Li Tian","year":"2020","unstructured":"Tian Li, Shengyuan Hu, Ahmad Beirami, and Virginia Smith. 2020. Federated multi-task learning for competing constraints. arXiv preprint arXiv:2012.04221 (2020).","journal-title":"arXiv preprint arXiv:2012.04221"},{"key":"e_1_3_5_25_2","volume-title":"International Conference on Machine Learning","author":"Li Tian","year":"2021","unstructured":"Tian Li, Shengyuan Hu, Ahmad Beirami, and Virginia Smith. 2021. Ditto: Fair and robust federated learning through personalization. In International Conference on Machine Learning."},{"key":"e_1_3_5_26_2","volume-title":"International Conference on Learning Representations","author":"Li Tian","year":"2019","unstructured":"Tian Li, Maziar Sanjabi, Ahmad Beirami, and Virginia Smith. 2019. Fair Resource Allocation in Federated Learning. In International Conference on Learning Representations."},{"key":"e_1_3_5_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/JCC49151.2020.00013"},{"key":"e_1_3_5_28_2","volume-title":"Advances in Neural Information Processing Systems Conference","author":"Lin Tao","year":"2020","unstructured":"Tao Lin, Lingjing Kong, Sebastian U. Stich, and Martin Jaggi. 2020. Ensemble distillation for robust model fusion in federated learning. In Advances in Neural Information Processing Systems Conference."},{"key":"e_1_3_5_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSC47296.2019.8937642"},{"key":"e_1_3_5_30_2","article-title":"Real-world image datasets for federated learning","author":"Luo Jiahuan","year":"2019","unstructured":"Jiahuan Luo, Xueyang Wu, Yun Luo, Anbu Huang, Yunfeng Huang, Yang Liu, and Qiang Yang. 2019. Real-world image datasets for federated learning. arXiv preprint arXiv:1910.11089 (2019).","journal-title":"arXiv preprint arXiv:1910.11089"},{"key":"e_1_3_5_31_2","article-title":"Threats to federated learning: A survey","author":"Lyu Lingjuan","year":"2020","unstructured":"Lingjuan Lyu, Han Yu, and Qiang Yang. 2020. Threats to federated learning: A survey. arXiv preprint arXiv:2003.02133 (2020).","journal-title":"arXiv preprint arXiv:2003.02133"},{"key":"e_1_3_5_32_2","first-page":"4274","volume-title":"International Conference on Machine Learning","author":"Mahloujifar Saeed","year":"2019","unstructured":"Saeed Mahloujifar, Mohammad Mahmoody, and Ameer Mohammed. 2019. Data poisoning attacks in multi-party learning. In International Conference on Machine Learning. 4274\u20134283."},{"key":"e_1_3_5_33_2","first-page":"1273","volume-title":"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 Artificial Intelligence and Statistics. PMLR 1273\u20131282."},{"key":"e_1_3_5_34_2","first-page":"4615","volume-title":"International Conference on Machine Learning","author":"Mohri Mehryar","year":"2019","unstructured":"Mehryar Mohri, Gary Sivek, and Ananda Theertha Suresh. 2019. Agnostic federated learning. In International Conference on Machine Learning. 4615\u20134625."},{"key":"e_1_3_5_35_2","volume-title":"International Conference on Learning Representations","author":"Peng Xingchao","year":"2019","unstructured":"Xingchao Peng, Zijun Huang, Yizhe Zhu, and Kate Saenko. 2019. Federated adversarial domain adaptation. In International Conference on Learning Representations."},{"key":"e_1_3_5_36_2","article-title":"Robust aggregation for federated learning","author":"Pillutla Krishna","year":"2019","unstructured":"Krishna Pillutla, Sham M. Kakade, and Zaid Harchaoui. 2019. Robust aggregation for federated learning. arXiv preprint arXiv:1912.13445 (2019).","journal-title":"arXiv preprint arXiv:1912.13445"},{"key":"e_1_3_5_37_2","article-title":"Dynamic federated learning model for identifying adversarial clients","author":"Rodr\u00edguez-Barroso Nuria","year":"2020","unstructured":"Nuria Rodr\u00edguez-Barroso, Eugenio Mart\u00ednez-C\u00e1mara, M. Luz\u00f3n, Gerardo Gonz\u00e1lez Seco, Miguel \u00c1ngel Veganzones, and Francisco Herrera. 2020. Dynamic federated learning model for identifying adversarial clients. arXiv preprint arXiv:2007.15030 (2020).","journal-title":"arXiv preprint arXiv:2007.15030"},{"key":"e_1_3_5_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054676"},{"key":"e_1_3_5_39_2","volume-title":"The Complete Works of William Shakespeare","author":"Shakespeare William","unstructured":"William Shakespeare. The Complete Works of William Shakespeare. Retrieved from http:\/\/www.gutenberg.org\/ebooks\/100\/."},{"key":"e_1_3_5_40_2","doi-asserted-by":"crossref","unstructured":"Shai Shalev-Shwartz and Shai Ben-David. 2014. Understanding Machine Learning: From Theory to Algorithms. Cambridge University Press.","DOI":"10.1017\/CBO9781107298019"},{"key":"e_1_3_5_41_2","article-title":"Byzantine-resilient secure federated learning","author":"So Jinhyun","year":"2020","unstructured":"Jinhyun So, Ba\u015fak G\u00fcler, and A. Salman Avestimehr. 2020. Byzantine-resilient secure federated learning. IEEE J. Select. Areas Commun. 39, 7 (2020), 2168\u20132181.","journal-title":"IEEE J. Select. Areas Commun."},{"key":"e_1_3_5_42_2","volume-title":"International Conference on Learning Representations","author":"Stich Sebastian U.","year":"2018","unstructured":"Sebastian U. Stich. 2018. Local SGD converges fast and communicates little. In International Conference on Learning Representations."},{"key":"e_1_3_5_43_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.165"},{"key":"e_1_3_5_44_2","first-page":"1","article-title":"The art of data augmentation","author":"Dyk David A. van","year":"2001","unstructured":"David A. van Dyk and Xiao-Li Meng. 2001. The art of data augmentation. J. Computat. Graphic. Statist. 10, 1 (2001), 1\u201350.","journal-title":"J. Computat. Graphic. Statist."},{"key":"e_1_3_5_45_2","volume-title":"NIPS Workshop on Computational Social Science and the Wisdom of Crowds","author":"Wais Paul","year":"2010","unstructured":"Paul Wais, Shivaram Lingamneni, Duncan Cook, Jason Fennell, Benjamin Goldenberg, Daniel Lubarov, David Marin, and Hari Simons. 2010. Towards building a high-quality workforce with mechanical turk. In NIPS Workshop on Computational Social Science and the Wisdom of Crowds. Citeseer."},{"key":"e_1_3_5_46_2","volume-title":"International Conference on Learning Representations","author":"Wang Hongyi","year":"2019","unstructured":"Hongyi Wang, Mikhail Yurochkin, Yuekai Sun, Dimitris Papailiopoulos, and Yasaman Khazaeni. 2019. Federated learning with matched averaging. In International Conference on Learning Representations."},{"key":"e_1_3_5_47_2","volume-title":"ICML Workshop on Coding Theory for Machine Learning","author":"Wang Jianyu","year":"2019","unstructured":"Jianyu Wang and Gauri Joshi. 2019. Cooperative SGD: A unified framework for the design and analysis of communication-efficient SGD algorithms. In ICML Workshop on Coding Theory for Machine Learning."},{"key":"e_1_3_5_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"e_1_3_5_49_2","doi-asserted-by":"publisher","DOI":"10.2200\/S00960ED2V01Y201910AIM043"},{"key":"e_1_3_5_50_2","article-title":"Applied federated learning: Improving Google keyboard query suggestions","author":"Yang Timothy","year":"2018","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 preprint arXiv:1812.02903 (2018).","journal-title":"arXiv preprint arXiv:1812.02903"},{"key":"e_1_3_5_51_2","first-page":"5650","volume-title":"International Conference on Machine Learning","author":"Yin Dong","year":"2018","unstructured":"Dong Yin, Yudong Chen, Ramchandran Kannan, and Peter Bartlett. 2018. Byzantine-robust distributed learning: Towards optimal statistical rates. In International Conference on Machine Learning. 5650\u20135659."},{"key":"e_1_3_5_52_2","first-page":"7085","volume-title":"International Conference on Machine Learning","author":"Yin Dong","year":"2019","unstructured":"Dong Yin, Ramchandran Kannan, and Peter Bartlett. 2019. Rademacher complexity for adversarially robust generalization. In International Conference on Machine Learning. PMLR, 7085\u20137094."},{"key":"e_1_3_5_53_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"e_1_3_5_54_2","first-page":"11450","volume-title":"Conference on Advances in Neural Information Processing Systems","author":"Zheng Shuai","year":"2019","unstructured":"Shuai Zheng, Ziyue Huang, and James Kwok. 2019. Communication-efficient distributed blockwise momentum SGD with error-feedback. In Conference on Advances in Neural Information Processing Systems. 11450\u201311460."}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3517821","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3517821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:05Z","timestamp":1750182545000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3517821"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,11]]},"references-count":53,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,10,31]]}},"alternative-id":["10.1145\/3517821"],"URL":"https:\/\/doi.org\/10.1145\/3517821","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,11]]},"assertion":[{"value":"2021-03-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-06-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}